Cybersecurity
Cybersecurity news — Friday 23 October 2026
144 stories from 10 sources, every one in English. Each links to its publisher.
-
Friday Squid Blogging: Increasing Squid Populations
Schneier on Security
This article in Nature argues that it’s due to an overfishing of predators and warming sea temperatures. As usual, you can also use this squid post to talk about the security stories in the news that I haven’t covered. Blog moderation…
-
Abandoned Popcorn Time app exposed millions of device to RCE attacks
BleepingComputer
Researchers remotely disabled a vulnerable updater in the abandoned Time4Popcorn app, a fork of the Popcorn Time BitTorrent client, closing a security flaw that could have allowed attackers to execute malicious code with elevated…
-
(Reliable)＆#x3f; php2shell exploitability, (Fri, Oct 23rd)
SANS ISC
Yesterday everyone was running around like crazy (me included :) because of the php2shell vulnerability.
-
Microsoft Teams to get AI-powered, context-aware phishing detection
BleepingComputer
Microsoft has announced plans to add AI-powered phishing detection to Teams messages starting in early November 2026. [...]
-
BlackX UEFI Bootkit Bypasses Secure Boot on Patched Windows Systems Missing Revocations
The Hacker News
Diplomatic organizations in Central Asia have been targeted by a sophisticated new Unified Extensible Firmware Interface (UEFI) bootkit called BlackX. The activity, which singled out diplomatic entities in Tajikistan, Uzbekistan, and…
-
Ruby Fixes Three Regex Engine Bugs Responsible for Four Critical GitLab RCE Flaws
The Hacker News
Ruby has released versions 4.0.9, 3.4.12, and 3.3.13 to fix three bugs in Onigmo, the regular expression engine built into the language. The bugs lie behind four critical security flaws that GitLab patched over the past month. GitLab found…
-
Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions
The Hacker News
Cybersecurity researchers have discovered an artificial intelligence (AI)-driven intrusion ecosystem run by affiliates of the INC and The Gentlemen ransomware groups. Central to the operation is an "Autonomous Red Team Kill Chain…
-
Microsoft: Windows Server 2016 reaches end of support in January
BleepingComputer
Microsoft says Windows Server 2016 will stop receiving security updates after it reaches the end of support in January 2027. [...]
-
Quest Diagnostics confirms data breach exposed patient records
BleepingComputer
American clinical laboratory company Quest Diagnostics disclosed that patient records have been exposed after a threat actor gained unauthorized access to its Quanum LSM system. [...]
-
Android lets you ‘bubble’ apps for easy access now – how it works
ZDNet Security
Keep your most-used apps accessible with this new feature.
-
Senators say targeted ads are a security risk. Ad groups say the critics are off base.
CyberScoop Asia
Two senators say that revelations about online targeted advertising being used as a vector for spyware infections underscore the need for better security practices in the industry. Some members of the advertising industry that were…
-
PHP shares mitigation for new RCE vulnerability with no patch
BleepingComputer
The PHP security team has shared mitigation measures for a new remote code execution vulnerability that affects systems with non-default configurations and has no patch. [...]
-
PHP2Shell: Haven’t patched yet? Take these steps now to mitigate
ZDNet Security
The PHP Project provides instructions to stop further RCE exploits in limited settings.
-
In Other News: Tor Exit Relays Hijacked, Banks Spot Rogue AI Agents, Self-Rebuilding macOS Ransomware
SecurityWeek
Noteworthy stories that might have slipped under the radar: Russia’s APT28 hit NATO defense firms, PingCAP source code stolen, ShinyHunters negotiator probe. The post In Other News: Tor Exit Relays Hijacked, Banks Spot Rogue AI Agents…
-
You gave your AI agent access, but who is giving it orders?
BleepingComputer
AI agents can be manipulated through malicious emails, websites, and plugins into executing commands, stealing data, or deleting files using their legitimate permissions. Gen Digital explains how its Agent Trust Hub helps protect agents…
-
Hackers Breach Enterprise Firewalls and VPNs, Exposing Over 70,000 Credentials
The Hacker News
Cybersecurity researchers have disclosed details of a large-scale campaign that has targeted exposed network edge devices such as Fortinet FortiGate and Palo Alto Networks GlobalProtect firewalls. "Artifacts from this investigation also…
-
Resident Evil maker Capcom warns of phishing after 11.7 million records exposed
Malwarebytes Labs
.kadence-column480618_38f885-ca > .kt-inside-inner-col{padding-top:20px;padding-right:20px;padding-bottom:10px;padding-left:20px;}.kadence-column480618_38f885-ca > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm…
-
PHP Vulnerability Wrap-Up, (Fri, Oct 23rd)
SANS ISC
This morning, we returned to Infocon Green. As usual, we are raising the Infocon to alert you to emerging situations requiring immediate attention. PHP fit that description. By now, you either know about it, or you probably never will, so…
-
HPE patches eight max severity RCE and auth bypass AOS flaws
BleepingComputer
Hewlett Packard Enterprise (HPE) released security updates to patch 72 vulnerabilities in the Aruba Operating System (ArubaOS), including eight maximum-severity authentication bypass and code execution issues. [...]
-
Mirai Botnet Operators Join PHP2Shell Attacks as ASLR Bypass Exploits Emerge
SecurityWeek
Researchers tie PHP2Shell attempts to a Mirai botnet and show an ASLR bypass, but no successful compromise has been confirmed yet. The post Mirai Botnet Operators Join PHP2Shell Attacks as ASLR Bypass Exploits Emerge appeared first on…
-
URGENT - PHP Warns of Another Unpatched RCE Two Days After Emergency PHP2Shell Patches
The Hacker News
PHP has warned of another way an attacker could run code on a web server, two days after it shipped emergency fixes for the critical PHP2Shell flaws. The new issue, assigned CVE-2026-115560, affects only web applications configured in an…
-
Russian-Linked Hackers Used New Mesh Network Backdoor in Destructive Ukraine Attack
The Hacker News
The Russian state-sponsored hacking group Sandworm teamed up with another threat actor to carry out a destructive wiping attack targeting a Ukrainian logistics company last year. According to ESET, the attack involved UAC-0099 (aka Earth…
-
Compromised TLS Certificates
Schneier on Security
The Indian CA eMudhra Limited has eight TLS certificates with laughably weak private keys : The compromised eMudhra keys were defective at a level that’s challenging the imagination of many of the engineers studying the incident. A normal…
-
China APT Uses AI Pentest Tool Artex in ConnectWise Attacks
SecurityWeek
The state-sponsored hackers targeted hundreds of organizations and gained privileged access to some environments. The post China APT Uses AI Pentest Tool Artex in ConnectWise Attacks appeared first on SecurityWeek .
-
ISC Stormcast For Friday, October 23rd, 2026 https://isc.sans.edu/podcastdetail/10148, (Fri, Oct 23rd)
SANS ISC
-
Attackers Exploit Third VeloCloud Orchestrator Zero-Day in Four Months
SecurityWeek
The critical-severity SQL injection flaw allows attackers to access privileged internal functionality and gain operator privileges. The post Attackers Exploit Third Arista VCO Zero-Day in Four Months appeared first on SecurityWeek .
-
Crime Stoppers chapter freezes tips after breach breaks anonymity promise
Malwarebytes Labs
A breach exposed personal information in supposedly anonymous crime reports. Now one Crime Stoppers chapter has stopped accepting tips because it cannot guarantee anonymity. Toronto Crime Stoppers, which works with the community, police…
-
Critical Flaw in Python’s Popular Pillow Image Library Allows Code Execution via a Crafted Image
The Hacker News
Pillow, the most widely used image library for Python, can be made to run operating system commands on a server by specifying the name of a file it is told to open. The flaw, CVE-2026-112900, is in the way Pillow handles EPS images, which…
-
Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances
The Hacker News
AI agents paying for API calls with the x402 SDKs could sign a payment for their full balance of a supported token if a malicious API asked for it, security firm V12 said on October 22. The cause was the SDKs' default client, which set no…
-
11 Million Impacted by Capcom Data Breach
SecurityWeek
The hackers stole 11 million email addresses from CAPCOM ID and changed the login passwords for 196 accounts. The post 11 Million Impacted by Capcom Data Breach appeared first on SecurityWeek .
-
Quest Diagnostics Reports Cyber Breach Affecting ‘Certain Patient Records’
SecurityWeek
In a regulatory filing, Quest Diagnostics reported unauthorized access to its Quanum Lab Services Manager, a platform where certain clients can place test orders. The post Quest Diagnostics Data Breach Exposed ‘Certain Patient Records’…
-
LiteLLM Compromised in Fresh Supply Chain Attack
SecurityWeek
Hackers used compromised GitHub CLI OAuth tokens to push and approve malicious packages on PyPI and Docker. The post LiteLLM Compromised in Fresh Supply Chain Attack appeared first on SecurityWeek .
-
Atlassian Patches 75 Flaws in Data Center and Server Products
SecurityWeek
Atlassian’s October bulletin lists 176 vulnerability entries, including 14 critical-severity issues, all in third-party components. The post Atlassian Patches 75 Flaws in Data Center and Server Products appeared first on SecurityWeek .
-
Researchers Demonstrate Node2Shell RCE Exploit on Node.js Build Using Crafted Brotli Data
The Hacker News
Malicious Brotli data can make an application on an official build of Node.js run attacker-supplied code, security researchers at Imperva have demonstrated. Their "Node2Shell" proof of concept ran code on the official Node.js 24.22.0 image…
-
PHP2Shell Exploit Attempts Hit Millions as Attackers Try to Deploy Mirai Malware
The Hacker News
Threat actors have been observed unsuccessfully attempting to exploit the newly disclosed PHP2Shell vulnerabilities to rope infected systems into a Mirai botnet variant called Potassium, as it emerges that weaponizing the flaws may be…
-
Iran’s Prince of Persia APT Hosts C＆C in US for First Time Since 2016
SecurityWeek
After a three-month lull, Prince of Persia hid a Tornado C&C server on US shared hosting, its first US-based server since 2016. The post Iran’s Prince of Persia APT Hosts C&C in US for First Time Since 2016 appeared first on SecurityWeek .
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
Obstacles to Weaponizing PHP2Shell Likely Constrain Immediate Widespread Exploitation
Crowdstrike Blog
-
Why Organizations Secure AI Agents with Falcon Guardian
Crowdstrike Blog
-
HiMark: Hierarchical and Controllable Multi-bit Watermarking for Large Language Models
arXiv cs.CR (Security)
arXiv:2610.30601v1 Announce Type: new Abstract: With the rapid adoption of large language models (LLMs) in text generation applications, it has become increasingly difficult to trace generated content and assign responsibility for its use…
-
Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
arXiv cs.CR (Security)
arXiv:2610.30516v1 Announce Type: new Abstract: In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as text transmitted to a decoder, who attempts to recover it. The success of…
-
Self-Evolving Static Analysis via LLM Pseudo-Labeling
arXiv cs.CR (Security)
arXiv:2610.30184v1 Announce Type: new Abstract: Security bugs often slip past static analysis not because they are impossible to detect, but because detection rules have not yet been written for the code in front of us. New frameworks…
-
Rank Ceiling for Twiddle-Perturbation Faults on the Forward NTT
arXiv cs.CR (Security)
arXiv:2610.30383v1 Announce Type: new Abstract: NIST standardised ML-KEM and ML-DSA in 2024 for post-quantum key establishment and digital signatures. Both compute forward number-theoretic transforms (NTTs) on secret polynomials. Published…
-
Weaponizing the Exit: Input Privacy Leakage via Exit Routing Manipulation in Multi-Exit Networks
arXiv cs.CR (Security)
arXiv:2610.31246v1 Announce Type: new Abstract: Multi-exit networks improve inference efficiency by allowing inputs to terminate early at intermediate exits. We identify a privacy vulnerability in cloud deployments of these networks: a…
-
Data-Void Exploits in Web-Searching LLMs
arXiv cs.CR (Security)
arXiv:2610.30365v1 Announce Type: new Abstract: Web-searching Large Language Models (LLMs) have changed how users seek online information: instead of sifting through ranked lists of links, users read synthesized answers. This shift creates…
-
ReDence: A Hybrid Agentic and Decision-Model Framework for Rapid, Evidence-Grounded Detection of Modern Social Engineering Scams
arXiv cs.CR (Security)
arXiv:2610.30963v1 Announce Type: new Abstract: Detecting online social engineering (SE) scams often requires examining website workflows, verifying claims against external sources, and connecting evidence across multiple pages. Existing…
-
How to Backdoor Image Knowledge Distillation
arXiv cs.CR (Security)
arXiv:2504.21323v4 Announce Type: replace Abstract: Knowledge distillation is widely used to transfer behavior from a large teacher model to a smaller student. It is often assumed to be safe when the teacher is clean, because classic…
-
Giskard : Byzantine Robust and Private Aggregation for Large-Scale Decentralized Learning
arXiv cs.CR (Security)
arXiv:2606.19129v2 Announce Type: replace Abstract: In decentralized learning, clients train a machine learning model while keeping their data locally and share their model parameters or gradients with a set of neighbors, making it…
-
OP-Print: Tracing Membership Imprints in On-Policy Self-Distillation
arXiv cs.CR (Security)
arXiv:2610.31616v1 Announce Type: cross Abstract: On-policy distillation has been widely adopted for alleviating the distribution mismatch of off-policy distillation. Self-distillation further removes the need for an external teacher by…
-
The Price of Safety: Benign-Case Utility and Token Overhead of Memory-Poisoning Defenses in LLM Agents
arXiv cs.CR (Security)
arXiv:2609.22818v2 Announce Type: replace Abstract: Memory-poisoning defenses for LLM agents are typically evaluated by how well they stop attacks, even though almost all traffic they encounter is benign. We measure their cost when no…
-
On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders
arXiv cs.CR (Security)
arXiv:2610.30345v1 Announce Type: cross Abstract: Neural receivers for 5G New Radio (NR) match classical model-based receivers in link-level performance, but their robustness to adversarial perturbations at the receiver input remains…
-
Does More Compute Make Every Adversarial Attack Transferable?
arXiv cs.CR (Security)
arXiv:2504.20310v3 Announce Type: replace-cross Abstract: Transferable attacks, or transferable jailbreaks, are a particularly strong version of adversarial examples that fool all defenders in a class. In this work, we study when more…
-
Detecting AI Training in Datacentre Power
arXiv cs.CR (Security)
arXiv:2610.30182v1 Announce Type: new Abstract: AI governance agreements require methods to detect large model training runs on a monitored computing cluster, without trusting the operator. We develop a method to detect synchronous model…
-
When EVM Defaults Break: Three SDK Patterns for UTXO-Family Wallets
arXiv cs.CR (Security)
arXiv:2610.30183v1 Announce Type: new Abstract: Mainstream Web3 SDKs (e.g., ethers.js, viem) bundle three coupled assumptions: an account-based ledger, a single secp256k1 signer, and input-selection-free transaction construction. These…
-
MPIDetector: Detecting Multi-modal Prompt Injection via LLM-based Reasoning
arXiv cs.CR (Security)
arXiv:2610.30202v1 Announce Type: new Abstract: With the rapid integration of Multi-modal Large Language Models (MLLMs) into real-world applications, Prompt Injection (PI) has emerged as a critical security threat. Attackers can conceal…
-
PhishGen: Understanding LLM Capabilities in Automated Phishing Website Generation
arXiv cs.CR (Security)
arXiv:2610.30226v1 Announce Type: new Abstract: Phishing relies on visual deception, traditionally requiring web-development skills or pre-built kits. LLMs erode this barrier by generating functional websites from natural-language prompts…
-
Who Patches the Lightning Network? Evidence from Release Lines in Gossip, 2023-2026
arXiv cs.CR (Security)
arXiv:2610.30350v1 Announce Type: new Abstract: Every implementation of Bitcoin's Lightning payment network disclosed security vulnerabilities in 2026, and every advisory told operators to upgrade. Whether they do has never been measured…
-
HAWC-Leak: Heterogeneous Architecture Workload Classification utilizing Side-Channel Leakage
arXiv cs.CR (Security)
arXiv:2610.30400v1 Announce Type: new Abstract: Modern heterogeneous computing platforms, which integrate general-purpose processors with specialized accelerators such as FPGAs, have become the standard for high-performance and embedded…
-
Model-intrinsic, Weight-level, and Training-free Spectral Fingerprinting for Large Language Models
arXiv cs.CR (Security)
arXiv:2610.30626v1 Announce Type: new Abstract: The increasing release and reuse of Large Language Models (LLMs) as open-weight checkpoints make model fingerprinting important for ownership protection and offline auditing. Existing…
-
MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition
arXiv cs.CR (Security)
arXiv:2610.30914v1 Announce Type: new Abstract: Despite recent advances, deepfake detectors remain vulnerable to adversarial examples, particularly in diverse, real-world settings. We propose MIG-COW, a novel adversarial attack framework…
-
BelT Block Cipher
arXiv cs.CR (Security)
arXiv:2610.31178v1 Announce Type: new Abstract: BelT is a block cipher with a 128-bit block size and a 256-bit key, developed in Belarus and adopted as part of the Belarusian national standard STB 34.101.31 for encryption and integrity…
-
AfterDeleteBench: Auditing Post-Deletion Information Persistence in LLM Agents
arXiv cs.CR (Security)
arXiv:2610.31366v1 Announce Type: new Abstract: Many LLM agents maintain external persistent memory and derive additional state from past interactions, such as summaries. Deleting an original memory record therefore need not remove…
-
Auditing the Hand-Written Inputs of Learned Access Control
arXiv cs.CR (Security)
arXiv:2610.31388v1 Announce Type: new Abstract: Learned access control is typically deployed behind two hand-built artefacts: a hard-deny set enforced by a small trusted shield, and a region map that decides which requests mined rules…
-
Social-HUMINT: An LLM-Augmented Unified Framework for Measuring Social Media Exposure
arXiv cs.CR (Security)
arXiv:2610.31573v1 Announce Type: new Abstract: In the post-API landscape, social-media profiling has become inexpensive and automated: Large Language Models (LLMs) can extract structured information from unstructured content and deduce…
-
JANUS: Agentic Cross-Language Fuzzing Harness Generation for Android Native Libraries
arXiv cs.CR (Security)
arXiv:2610.30218v1 Announce Type: cross Abstract: Modern Android apps extensively rely on native libraries, bridging Java/Kotlin and C/C++ through the Java Native Interface (JNI). This cross-language interoperation, however, exposes the…
-
DLT Terms 100: a learner's glossary based on ISO 22739:2024
arXiv cs.CR (Security)
arXiv:2610.30596v1 Announce Type: cross Abstract: We propose ``DLT Terms 100'' aimed at improving literacy regarding blockchain (distributed ledger technology: DLT). The pace of DLT's social implementation has been slower than initially…
-
AgentTriage: Replayable Security Diagnosis Across Heterogeneous Agent Runtimes
arXiv cs.CR (Security)
arXiv:2610.30738v1 Announce Type: cross Abstract: When tool-use agents write files, execute code, or send data, their final responses do not explain the resulting security events, and heterogeneous runtimes expose the relevant evidence…
-
Homomorphic Encryption with Coset Code Construction
arXiv cs.CR (Security)
arXiv:2610.31437v1 Announce Type: cross Abstract: Homomorphic encryption enables computation on input data without decrypting it. This paper extends a construction based on scalar message codes, utilizing coset codes to pack $k$ message…
-
PAGE404: Breaking GPU Isolation Through Hardware-assisted Page Migration
arXiv cs.CR (Security)
arXiv:2610.20962v3 Announce Type: replace Abstract: NVIDIA's Grace Hopper (GH200) superchip represents a new generation of heterogeneous computing, tightly integrating a 72-core Arm-based CPU with a Hopper GPU on a single module via a…
-
Measuring the Permission Gate: A Stress-Test Evaluation of Claude Code's Auto Mode
arXiv cs.CR (Security)
arXiv:2604.04978v3 Announce Type: replace-cross Abstract: Claude Code's auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4%…
-
No Edges, No Verdict: A Large-Scale Empirical Study of Declared Dependency Graphs in 78K SBOMs in the Wild
arXiv cs.CR (Security)
arXiv:2607.22140v3 Announce Type: replace-cross Abstract: Software Bills of Materials (SBOMs) are consumed not only as component inventories but as dependency graphs: vulnerability triage, reachability filtering, and impact analysis all…
-
RetryBench: Separating Retry Permission from Recovery Outcomes in GPT Tool Use
arXiv cs.CR (Security)
arXiv:2610.15884v3 Announce Type: replace-cross Abstract: False retry permission (FRP) occurs when an agent retries a timed-out tool call without support from the visible contract. RetryBench separates this error from realized recovery…
-
Automated screening of privacy risks in medical AI
arXiv cs.CR (Security)
arXiv:2610.30229v1 Announce Type: cross Abstract: Medical artificial intelligence (AI) models are often shared without their training data, assuming this protects the patients who contributed them. However, a model can reveal whether a…
-
Membership Inference Attack on Private Evolution
arXiv cs.CR (Security)
arXiv:2610.30514v1 Announce Type: new Abstract: Synthetic Data Generation (SDG) is an actively studied way to enable safe sharing of private data more broadly. Inference-only SDG methods, such as Private Evolution (PE), are particularly…
-
Structural cryptanalysis of classic McEliece: Assessment of claims, costs and evidence
arXiv cs.CR (Security)
arXiv:2610.31196v1 Announce Type: new Abstract: For the last two years, classical structural attacks on McEliece with binary Goppa codes progressed further, at the parameters of Classic McEliece, than in the previous four decades: a…
-
MarkTune: Improving the Quality-Detectability Trade-off in Model-Embedded LLM Watermarking
arXiv cs.CR (Security)
arXiv:2512.04044v2 Announce Type: replace-cross Abstract: Language model watermarking schemes fall into two broad categories: inference-time methods, which modify the decoding process at generation time, and model-embedded methods, which…
-
Mirage: Targeted Jailbreaks Against Post-Generation Safety Checkers in Multimodal Diffusion Models
arXiv cs.CR (Security)
arXiv:2610.30348v1 Announce Type: new Abstract: Post-generation safety checkers are widely employed in diffusion-model pipelines to prevent unsafe generated content from reaching users. In this paper, we show that these safety checkers can…
-
Beyond the Turing threshold: Productive grammars generate essentially undecidable languages
arXiv cs.CR (Security)
arXiv:2609.11385v2 Announce Type: replace-cross Abstract: Emil Post's productive sets are not even semi-computable, let alone computable, being thus essentially incomputable. Accordingly, formal languages whose set of words is a…
-
Efficient and Optimal Learning of Discrete Distributions with Person-Level Privacy
arXiv cs.CR (Security)
arXiv:2610.31612v1 Announce Type: cross Abstract: We study learning a discrete distribution under person-level differential privacy in the batched setting. Given $n$ users, each contributing $m$ i.i.d. samples from an unknown distribution…
-
Metamorphism: A mathematical challenge for antivirus technology
arXiv cs.CR (Security)
arXiv:2608.27007v2 Announce Type: replace Abstract: Metamorphic viruses, currently the most advanced computer viruses in the wild, have the unique ability of mutating their own code virtually into infinitely many highly dissimilar copies…
-
Federated Differentially Private Optimization via Low-Rank Preconditioning
arXiv cs.CR (Security)
arXiv:2610.31069v1 Announce Type: cross Abstract: We consider differentially private (DP) optimization in the federated setting, where a DP estimate of the feature covariance matrix serves as a Hessian approximation for generalized linear…
-
Your Token Is Gone: A Token-Consumption Countermeasure for Disrupting LLM-Based Scam Systems
arXiv cs.CR (Security)
arXiv:2610.30666v1 Announce Type: new Abstract: LLM-based scam systems increasingly combine adaptive dialogue, persistent context, external tools, and multi-agent coordination to automate personalized fraud. These capabilities also create…
-
Can Loan Processors and Underwriters Spot AI-Edited Statements? An Empirical Study
arXiv cs.CR (Security)
arXiv:2610.30758v1 Announce Type: cross Abstract: AI-assisted editing can produce loan documents that preserve familiar issuer layouts while changing the applicant's identity. We investigated whether experienced underwriters and loan…
-
Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
arXiv cs.CR (Security)
arXiv:2610.30193v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, source reconstruction, unauthorized access, data poisoning, and prompt…
-
Not Where You Think: Protecting Location Privacy Against Reasoning-Based Geolocation
arXiv cs.CR (Security)
arXiv:2610.30439v1 Announce Type: new Abstract: Recent large reasoning models can infer where ordinary photos were taken using only visual information, creating a serious location privacy risk even when metadata and obvious geographic…
-
SecLog-Bench: A Scalable Benchmark for Cybersecurity Log Reasoning with Scaffolded Evidence
arXiv cs.CR (Security)
arXiv:2610.31000v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for cybersecurity, leading to growing interest in LLM-based automated cybersecurity log analysis. However, current datasets (1) are…
-
WildFakeToolBench: Benchmarking AI-Generated Image Detectors with Web-Sourced Image Processing
arXiv cs.CR (Security)
arXiv:2610.31152v1 Announce Type: cross Abstract: As AI generated images are getting popular these days, discussions on such generations are widely existed in current public forums, software repositories, and photography tutorials…
-
AgentPhishing: A Benchmark of LLM Email Agents Under Adaptive Attack
arXiv cs.CR (Security)
arXiv:2610.31404v1 Announce Type: new Abstract: Computer-use agents increasingly handle private information and act on users' behalf across desktop and web applications, including email. Phishing therefore poses privacy and security risks…
-
HPQ-AKE: A Provably Secure Sign-Less Hybrid Authenticated Key Exchange Protocol for Bandwidth-Constrained IoT and Edge Networks
arXiv cs.CR (Security)
arXiv:2610.12024v2 Announce Type: replace Abstract: Securing bandwidth-constrained Internet of Things (IoT) and edge networks during post-quantum migration creates an authentication trade-off: ML-KEM provides post-quantum key…
-
The Psychology of an AI Hacker
arXiv cs.CR (Security)
arXiv:2610.30361v1 Announce Type: new Abstract: Human hackers rely on composure, persistence, vigilance, and confidence under pressure. We investigate whether analogous emotion representations in AI models can improve cybersecurity AI…
-
FVQKD: A Formal Verification of Quantum Key Distribution Security in Rocq
arXiv cs.CR (Security)
arXiv:2610.30645v1 Announce Type: cross Abstract: Quantum key distribution (QKD), whose security is derived from quantum mechanics rather than computational assumptions, is moving into standardization and commercial deployment. Yet its…
-
Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
arXiv cs.CR (Security)
arXiv:2610.30418v1 Announce Type: new Abstract: Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled from them. This mosaic effect creates a critical risk for agents…
-
Beyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM Jailbreaks
arXiv cs.CR (Security)
arXiv:2610.26589v2 Announce Type: replace Abstract: Attack success rate (ASR) evaluates jailbreaks against large language models without accounting for repeated calls to the victim model. Yet each additional call gives the deployed system…
-
Amplifying Latency and Cost of LLM Inference via Rowhammer Attack
arXiv cs.CR (Security)
arXiv:2610.30798v1 Announce Type: new Abstract: Large language models (LLMs) achieve high inference efficiency using optimized GPU kernels generated by just-in-time (JIT) compilation frameworks such as Triton. Triton compiles GPU kernels…
-
Practical Auditing of Differentially Private Graph Release Mechanisms: Methodology, Toolkit, and Case Study
arXiv cs.CR (Security)
arXiv:2610.31294v1 Announce Type: new Abstract: Differential Privacy (DP) has become a prominent approach for protecting graph data releases, yet empirical auditing methodologies have largely been developed for tabular datasets and machine…
-
ARMOR: Adversary Cost Amplification via a Schema-Preserving Password-Hardening Retrofit for Resource-Constrained Systems
arXiv cs.CR (Security)
arXiv:2610.14300v2 Announce Type: replace Abstract: Credential-database disclosure exposes Internet of Things gateways, edge servers and legacy verifiers to offline password guessing. Memory-hard key derivation functions (KDFs) are…
-
DEFEAT: Stitching Fragmented File I/O Contexts for Early Ransomware Detection
arXiv cs.CR (Security)
arXiv:2609.21426v2 Announce Type: replace Abstract: Ransomware increasingly fragments its file operations across temporary and intermediate files, scattering the semantic context that links individual I/O events to an overarching…
-
SecDT: A Profile-Based Security Layer for TRDP Communications
arXiv cs.CR (Security)
arXiv:2609.03133v2 Announce Type: replace Abstract: The Train Real-time Data Protocol (TRDP) is widely used on rolling stock but it provides limited native support for cryptographic protection. Furthermore, the multicast traffic profile…
-
Bridging Number-Theoretic Primality Testing And Algorithmic Optimization: An Adaptive Cryptographic Framework
arXiv cs.CR (Security)
arXiv:2610.30935v1 Announce Type: new Abstract: The security of modern public-key cryptographic systems, such as RSA, Diffie-Hellman, and ECC, depends entirely on the computational intractability of the integer factorization and discrete…
-
Bridging the Closed-World Gap: Interpretable Anomaly Detection via a Hybrid TSK-FCM Ensemble on the BETH Dataset
arXiv cs.CR (Security)
arXiv:2610.30576v1 Announce Type: new Abstract: A fundamental paradox plagues the deployment of Machine Learning in cybersecurity: supervised models generalize poorly to novel, Out-of-Distribution (OoD) attacks, whereas unsupervised models…
-
Temporal Liquidity Crossing for Blockchains: An EIP-1559 Extension for Admission Below the Base Fee
arXiv cs.CR (Security)
arXiv:2610.30595v1 Announce Type: cross Abstract: Transactions differ in how their value changes with execution time and relative position. Ethereum's EIP-1559 lets them compete through fee fields, but a fee bid gives no enforceable claim…
-
An Orchestrated Sandbox for Side-Channel Analysis of Cyber-Physical Systems Malware
arXiv cs.CR (Security)
arXiv:2508.14261v2 Announce Type: replace Abstract: Embedded devices powering cyber-physical systems (CPS) are increasingly internet-exposed, placing critical infrastructure under active threat. Dynamic analysis of embedded malware…
-
Evolving Federated Density Peak Clustering with Shuffler-Based Anonymization
arXiv cs.CR (Security)
arXiv:2610.31211v1 Announce Type: cross Abstract: In this paper, we present a novel one-shot federated clustering approach based on evolving fuzzy clustering and shuffler-based anonymization. In federated clustering, each round reveals…
-
Parameters efficient language model with latent cross-attention for IoT intrusion detection
arXiv cs.CR (Security)
arXiv:2610.30222v1 Announce Type: new Abstract: Language models have shown strong potential for intrusion detection, but their high memory and computational demands make them difficult to deploy in resource-constrained IoT environments. In…
-
Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
arXiv cs.CR (Security)
arXiv:2610.28315v2 Announce Type: replace Abstract: Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes in this memory pose a privacy risk if exposed. We ask how consulting…
-
MCP vs CLI for AI Agents: A Comparative Analysis of Tool Integration Strategies for Autonomous Systems
arXiv cs.CR (Security)
arXiv:2610.30157v1 Announce Type: cross Abstract: AI agents require interfaces to interact with external systems such as files, APIs, databases, and cloud services. Two competing paradigms have emerged: CLI (Command Line Interface), where…
-
Scaling Laws for Safety Probes
arXiv cs.CR (Security)
arXiv:2610.30678v1 Announce Type: cross Abstract: Safety probes trained on a model's activations are a standard tool for monitoring language models in real time. Each time a new model is released or a new harm area needs to be monitored…
-
Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning
arXiv cs.CR (Security)
arXiv:2609.20650v2 Announce Type: replace-cross Abstract: Federated learning enables collaborative training without sharing patient-level data, but most studies remain simulations. Based on five requirements derived from the literature, we…
-
Computer Science Conferences Should Require Nonrepudiable Experimental Results
arXiv cs.CR (Security)
arXiv:2605.08586v3 Announce Type: replace Abstract: This position paper argues that computer science conferences should require tamper-evident, nonrepudiable attestations of experimental results. We name the underlying problem experiment…
-
XIR: A Framework for Interoperability across Cross-Chain Protocols Based on a Verifiable Intermediate Representation
arXiv cs.CR (Security)
arXiv:2609.20010v5 Announce Type: replace Abstract: Cross-chain protocols enable applications to exchange messages across blockchains. Under point-to-point configurations, communication depends on a direct connection between the source and…
-
AIRO: A Streaming-Based Machine Learning Framework for Threat Detection and Security in Industrial Internet of Things
arXiv cs.CR (Security)
arXiv:2610.30713v1 Announce Type: new Abstract: Modern Industrial Internet of Things (IIoT) im- plementations now connect edge gateways, cloud dashboards and business applications. This improves visibility and remote monitoring. However it…