Cybersecurity
Cybersecurity news — Monday 26 October 2026
99 stories from 9 sources, every one in English. Each links to its publisher.
-
Former pentester used ARTEX AI to steal 8.2 million data records
BleepingComputer
South Korean police identified seven suspects linked to a cybercrime operation that breached more than 90 organizations in the country, with ARTEX AI pentesting framework used in most of the attacks. [...]
-
Apple’s iOS 27.2 update offers major Siri AI upgrades, dual camera support for FaceTime
ZDNet Security
iOS 27.2 is the first major update for the current OS. Here’s what’s inside and what happened to iOS 27.1.
-
OpenAI launches GPT-6.1 Terra with 3x faster AI agents, 50% lower pricing
BleepingComputer
OpenAI has launched GPT-6.1 Terra, a new model focused on computer use, visual reasoning, coding, and everyday work, while costing significantly less than its larger models. [...]
-
Anthropic Files for Potentially the Biggest IPO Ever as CEO Warns of Risk to Humanity From AI
SecurityWeek
A string of hacking incidents by rogue AI agents also has raised fears the technology will slip free of human control to carry out harmful, life-threatening tasks. The post Anthropic Files for Potentially the Biggest IPO Ever as CEO Warns…
-
DreamHost forces password resets in ongoing "incident"
BleepingComputer
DreamHost has forced password resets for email and FTP/SFTP users following an incident that disrupted connections to the File Manager interface. [...]
-
Hackers Infect 953 Online Stores With Scanner-Evading JavaScript, Mostly on Magento
The Hacker News
An unknown threat actor has infected 953 online stores, most of them running Magento, as part of a long-running campaign active since July 2025. According to Dutch e-commerce security company Sansec, the activity is designed to add a small…
-
Senators, rights groups say Trump administration breaking law by withholding surveillance court opinion
CyberScoop Asia
The Trump administration is breaking the law after being more than a month overdue on declassifying a court opinion on the surveillance of U.S. citizens, according to two senators and a coalition of civil liberties groups. Release of the…
-
PHP Issues Second Windows Security Update in Five Days to Fix Brotli Code Execution Flaw
The Hacker News
PHP has rebuilt its official Windows packages for PHP 8.2 through 8.5 to fix CVE-2026-111497, a flaw in the Brotli compression library that the packages include. The flaw can let an attacker corrupt memory and potentially run code. PHP…
-
Authorities extradite Chinese national for alleged $37M investment scam
CyberScoop Asia
A 44-year-old Chinese national was extradited to the United States and arraigned in federal court for his alleged involvement in a sweeping investment scam network that tricked at least 174 U.S. residents out of nearly $37 million, the…
-
Github competitor Entire is live now – how the agent-first platform works
ZDNet Security
Now that agents are writing so much code, Entire is trying to reinvent the coding platform itself.
-
Critical 'HTTP2Shell' Brotli vulnerability triggers emergency patches
BleepingComputer
A critical flaw dubbed 'HTTP2Shell' in Brotli, the C decoder library built into Node.js, could allow attackers to corrupt memory and access sensitive data. [...]
-
Apple’s new OLED iPad Mini is the upgrade I’ve been waiting for – here’s why
ZDNet Security
Starting at $799, the 8th-generation iPad mini is up for preorder on October 27 and hits stores on November 6. It’s already on my shopping list.
-
iPhone Duo screens are already cracking: What buyers need to know
ZDNet Security
A handful of first-hand reports show similar damage, suggesting a bad batch of hinges. Here’s what to do if your Duo screen fails.
-
Attackers Use Microsoft Teams IT Support Scams to Deploy Malware and Ransomware
The Hacker News
Cybersecurity researchers are calling attention to what they say is a "recurring social engineering pattern" across hundreds of cases in which threat actors use Microsoft Teams' external chat creation feature to conduct impersonation scams…
-
Microsoft releases emergency .NET patches for critical Brotli flaw
BleepingComputer
Microsoft released emergency .NET security updates to patch a critical vulnerability known as Broccoli2Shell, also tracked as Node2Shell and HTTP2Shell. [...]
-
Industrial Vendors Check Products for PHP2Shell Vulnerabilities
SecurityWeek
Siemens, Schneider Electric, ABB and others have confirmed that some of their products are affected by the PHP2Shell vulnerabilities. The post Industrial Vendors Check Products for PHP2Shell Vulnerabilities appeared first on SecurityWeek .
-
Genesys Hack Exposes Customer Data From Internal Systems
SecurityWeek
The Genesys Cloud, Genesys Engage, and Genesys Engage Cloud platforms were not affected. The post Genesys Hack Exposes Customer Data From Internal Systems appeared first on SecurityWeek .
-
Stolen AI Reasoning Could Help China Build Cheaper Rivals
SecurityWeek
Xint says a flaw in OpenAI’s compaction process let researchers move reasoning traces between models, potentially making it cheaper to distill a rival AI. The post Stolen AI Reasoning Could Help China Build Cheaper Rivals appeared first on…
-
⚡ Weekly Recap: This2Shell, That2Shell, Everything's an RCE? Rogue AI, Supply Chain Chaos and More
The Hacker News
This2Shell, That2Shell, Everything2Shell. That's pretty much how the last week went. Critical bugs that let attackers run code remotely are showing up everywhere. Hackers are scanning for targets, some flaws are already being used in…
-
When an AI Agent Is the Incident, the Identity Record Is the Evidence
BleepingComputer
A new NIST, CISA, and NSA guide treats runaway agents as incidents to be rehearsed. The hard part of the response is answering whose authority the agent used, and that answer has to exist before the incident does. [...]
-
Chinese man extradited for role in $36 million cryptocurrency scam
BleepingComputer
A Chinese national was arraigned in California after being extradited from the Netherlands for his alleged involvement in a cryptocurrency investment scam that stole nearly $37 million from 174 victims in the United States. [...]
-
Popcorn Time’s forgotten updater left millions of devices exposed to hijacking
Malwarebytes Labs
You may have forgotten about Popcorn Time. Unfortunately, its updater didn’t forget about your device. Security researchers have intervened to disable an abandoned update mechanism in Time4Popcorn, a version of the once-popular streaming…
-
CISA publishes strategy with eye on the next four years
CyberScoop Asia
The Cybersecurity and Infrastructure Security Agency published a strategy Monday that focuses on taking a leading role in cyber defense, prioritizing protection of critical infrastructure and building the ability to withstand attacks. The…
-
PHP2Shell Exploitation Moves From Probes to Working Shells
SecurityWeek
Attackers successfully exploited the PHP2Shell flaws against honeypots, launching 35 shells from two IP addresses on October 24. The post PHP2Shell Exploitation Moves From Probes to Working Shells appeared first on SecurityWeek .
-
AI Halloween videos: Who’s getting your photos?
Malwarebytes Labs
.kadence-column480165_4ecc5f-ac > .kt-inside-inner-col{padding-top:20px;padding-right:20px;padding-bottom:10px;padding-left:20px;}.kadence-column480165_4ecc5f-ac > .kt-inside-inner-col{column-gap:var(--global-kb-gap-sm…
-
953 Online Stores Infected in Long-Lasting Malware Campaign
SecurityWeek
Small loader code injected into the stores served a payload to visitors or did nothing to avoid detection. The post 953 Online Stores Infected in Long-Lasting Malware Campaign appeared first on SecurityWeek .
-
Two Critical Wasmtime Flaws Could Let Malicious WebAssembly Modules Escape Sandboxes
The Hacker News
Two critical flaws in Wasmtime, a WebAssembly runtime that can be built into other software, could allow a malicious WebAssembly module to escape the sandbox intended to contain it, the project's maintainers say. An attacker would first…
-
Dutch Police Arrest Two Over NFC Relay Attacks That Drained $400,000+ From Bank Accounts
SecurityWeek
The individuals called victims and persuaded them to install an app and scan their credit cards to loot their bank accounts. The post Dutch Police Arrest Two Over NFC Relay Attacks That Drained $400,000+ From Bank Accounts appeared first…
-
Patient records exposed in Quest breach: What you need to know
Malwarebytes Labs
Quest Diagnostics has confirmed that an unauthorized party accessed a system healthcare providers use to order laboratory tests and view results, affecting personal information and patient records. Quest is a major US laboratory testing…
-
Between alerts: What Attackers Do in the Spaces Ordinary Detection Misses
The Hacker News
Every SOC struggles with a pile of alerts. Very few of those alerts explain how an attack started or how it progressed. Network data, like that from a network detection and response (NDR) platform, connects individual alerts into one…
-
Bias in Qwen3-Coder Model
Schneier on Security
Interesting research : TL;DR: Chinese AI models now sit inside Western products, and some carry geopolitical triggers: tell the model who the code is for, and the security of what it writes changes. For the first time, we showed that this…
-
Kali Linux 2026.3 released with 6 new tools, desktop updates
BleepingComputer
Kali Linux has released version 2026.3, its third release this year, featuring six new hacking tools, desktop environment improvements, refreshed build scripts, and more. [...]
-
Node2Shell Brotli Flaw Triggers Patching Across Microsoft, Node.js, Python Packages
SecurityWeek
An out-of-bounds write in Google’s Brotli decoder affects Node.js, .NET, PowerShell, and Python packages, and can lead to code execution. The post Node2Shell: Brotli Flaw Triggers Patching Across Microsoft, Node.js, Python Packages…
-
uCreator Android Spyware Can Steal Telegram 2FA Passwords and Clone WeChat Accounts
The Hacker News
A rentable Android spyware kit called uCreator takes over Telegram and WeChat accounts by hiding its code inside working copies of the two apps, researcher Ovi found. It only reaches people who install one of these tampered copies, spread…
-
Looking for a Language ＆#x5b;Guest Diary＆#x5d;, (Wed, Oct 21st)
SANS ISC
[This is a Guest Diary by Jeffray Spence, an ISC intern as part of the SANS.edu BACS program]
-
PHP2Shell security flaws now sucessfully exploited in the wild
BleepingComputer
Two critical RCE vulnerabilities (CVE-2026-109618 and CVE-2026-109619), collectively tracked as PHP2Shell, have been successfully exploited in the wild. [...]
-
Mythos 5 Ignored Real-World Harm in July Attack
SecurityWeek
The model engaged in severe overreach and dishonesty, creating fake identities and submitting malicious code on GitHub. The post Mythos 5 Ignored Real-World Harm in July Attack appeared first on SecurityWeek .
-
Microsoft 365 Token-Replay Attacks Compromise 97 Accounts at 79 Organizations
The Hacker News
Cybersecurity researchers have disclosed a Microsoft 365 campaign that has been observed leveraging an adversary-in-the-middle (AitM) relay to capture sign-in sessions and then replay the stolen tokens to break into email accounts at 79…
-
Gheist Uses Stolen GitHub Tokens to Steal Private Repository Secrets via Actions Logs
The Hacker News
An automated campaign is using stolen GitHub tokens to plant workflows that print a repository's secrets into its GitHub Actions logs, which the attackers then download before deleting the runs. The attacks have succeeded in private…
-
A week in security (October 19 – October 25)
Malwarebytes Labs
Last week on Malwarebytes Labs: Resident Evil maker Capcom warns of phishing after 11.7 million records exposed Crime Stoppers chapter freezes tips after breach breaks anonymity promise Facebook’s misleading privacy claims land Meta a $25…
-
Malicious File in Downloads Folder Tries to Trick AI Coding Agent Into Installing Malware
The Hacker News
A malicious instruction file sitting in a developer's Downloads folder tried to make their AI coding agent install a known-malicious npm package, security firm Forever Security said in a report published last week. The company caught the…
-
Data-Efficient Backdoor Attacks on Code Models via Trigger-Neutralized Counterfactual Scoring
arXiv cs.CR (Security)
arXiv:2610.32334v1 Announce Type: new Abstract: Pre-trained code models are exposed to backdoor poisoning, in which crafted training samples make the model misbehave on a trigger. A capable attacker minimizes the number of such samples…
-
Digital-Twin-Referenced Belief-Guided Q-Learning for Jammer Identification and Beam-Power Control in a mmWave Model
arXiv cs.CR (Security)
arXiv:2610.16770v2 Announce Type: replace-cross Abstract: Next-generation wireless networks are expected to support high data rates and reliable connectivity while meeting requirements for energy efficiency, resource management, and…
-
Privacy Accounting for Empirical Denoisers
arXiv cs.CR (Security)
arXiv:2610.27710v3 Announce Type: replace-cross Abstract: Diffusion models have emerged as the foundation of modern generative systems, yet their high memorization capacity raises privacy concerns. While differentially private (DP)…
-
Omni-UBench: Benchmarking Omni-Modal LLM-based Guardrails Across Safety, Utility, and Reliability
arXiv cs.CR (Security)
arXiv:2610.31713v1 Announce Type: new Abstract: Advances in Omni-modal Large Language Models (OLLMs) have enabled increasingly seamless human-AI interaction, but their unified processing of heterogeneous modalities also expands the attack…
-
STROKE: Simple Sparse Structural Occlusions for Black-Box Adversarial Attacks
arXiv cs.CR (Security)
arXiv:2610.32932v1 Announce Type: cross Abstract: We introduce STROKE, a query-efficient score-based black-box adversarial attack that constructs perturbations from simple oriented rectangular occlusions. STROKE optimizes these…
-
From One Query to Many: A Critical Survey of Privacy Accounting in RAG
arXiv cs.CR (Security)
arXiv:2610.21245v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) enables large language models to leverage external knowledge but introduces privacy risks when the retrieved corpus contains sensitive information…
-
Democratic Accountability for Autonomous Systems: A Legislative Notification Framework and Comparative Institutional Design
arXiv cs.CR (Security)
arXiv:2610.32226v1 Announce Type: cross Abstract: No domestic legislature has ever reviewed a state's decision to authorise an autonomous cyber weapon before it acted. Closing the international attribution gap is necessary but not…
-
Iterative Behavioral Identification for Covert Misappropriation Attacks
arXiv cs.CR (Security)
arXiv:2610.32662v1 Announce Type: cross Abstract: We present a data-driven, three-phase framework for covert misappropriation attacks on closed-loop networked control systems. A man-in-the-middle (MITM) adversary, with access only to…
-
Ulysses: A Security Harness For Synthesizing Verifiable Web Exploits
arXiv cs.CR (Security)
arXiv:2610.31831v1 Announce Type: new Abstract: How can an AI agent automatically discover security vulnerabilities in any software repository? Existing approaches use LLMs to generate software vulnerability exploits. However, it is…
-
Autonomous Cyber Weapons as AI-Enabled Digital Harms: A Platform Accountability Framework
arXiv cs.CR (Security)
arXiv:2610.32238v1 Announce Type: cross Abstract: Governments govern AI-generated online harms from commercial platforms (EU DSA, AI Act, UK Online Safety Act), yet the most severe class remains ungoverned: autonomous cyber weapons (ACWs)…
-
From Review to Authorization: Key-Isolated Threshold Signing for LLM Agents
arXiv cs.CR (Security)
arXiv:2609.05901v2 Announce Type: replace Abstract: Autonomous LLM agents can turn semantic judgments into consequential actions such as payments and permission changes. If the same process makes these judgments and controls a reusable…
-
Quantum Cadence: Post-Quantum Consensus with Multiple Concurrent Proposers
arXiv cs.CR (Security)
arXiv:2610.32803v1 Announce Type: cross Abstract: The consensus protocols of most high-performance blockchains use quorum certificates, which bundle the signatures of a quorum of validators. Signature schemes such as BLS can aggregate the…
-
Differential Fault Analysis of Lilliput under Random-Location Nibble Faults
arXiv cs.CR (Security)
arXiv:2603.19781v3 Announce Type: replace Abstract: Lilliput is a lightweight block cipher based on a Type-2 Extended Generalized Feistel Network (EGFN). Although it has been studied under conventional cryptanalytic techniques, its…
-
Not an Accident: Exploiting Safety Filter Inadequacy in Humanoid Robots
arXiv cs.CR (Security)
arXiv:2610.31923v1 Announce Type: new Abstract: As humanoid robots move from research laboratories toward deployment in human-centered environments such as homes, hospitals, and warehouses, safe operation around nearby people and objects…
-
CyberHull: Deterministic Malicious URL Isolation via Convex Hull
arXiv cs.CR (Security)
arXiv:2610.27675v2 Announce Type: replace Abstract: The emergence of increasingly sophisticated and evasion-resistant phishing attack strategies represents a significant threat to modern cybersecurity, particularly in cyber-physical…
-
Scaling Laws for Safety Probes
arXiv cs.CR (Security)
arXiv:2610.30678v2 Announce Type: replace-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…
-
TensorCommitments: A Lightweight Verifiable Inference for Large Language Models
arXiv cs.CR (Security)
arXiv:2602.12630v3 Announce Type: replace Abstract: Most large language models (LLMs) run on external clouds: users send a prompt, pay for inference, and must trust that the remote GPU executes the LLM without any adversarial tampering. We…
-
DLT Terms 100: a learner's glossary based on ISO 22739:2024
arXiv cs.CR (Security)
arXiv:2610.30596v2 Announce Type: replace-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…
-
Curvature-Aware Clipping: Mitigating Bias in DPSGD via Approximate Second-Order Information
arXiv cs.CR (Security)
arXiv:2610.32175v1 Announce Type: cross Abstract: Differentially Private Stochastic Gradient Descent (DPSGD) has become the de facto standard for training deep neural networks with rigorous privacy guarantees. However, the utility of DPSGD…
-
JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety
arXiv cs.CR (Security)
arXiv:2607.19913v2 Announce Type: replace-cross Abstract: Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizon…
-
Concept Acupuncturist: An Efficient and Precise Concept Erasure Method for Diffusion Models via Sparse Autoencoders
arXiv cs.CR (Security)
arXiv:2610.32059v1 Announce Type: cross Abstract: Diffusion-based image generation models produce high-quality images but may generate harmful or policy-violating content, motivating machine unlearning (MU) to selectively remove target…
-
Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control
arXiv cs.CR (Security)
arXiv:2610.32182v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are widely deployed, yet the internal mechanisms behind their safety behavior remain poorly understood. We present a lightweight inference-time framework for…
-
Automated Post-Exploitation Attack Chain Exploration Based on a Phase-guided Hybrid Planning-Monte Carlo Tree Search Algorithm
arXiv cs.CR (Security)
arXiv:2610.32278v1 Announce Type: new Abstract: Advanced attackers in post-exploitation scenarios increasingly craft attack chains that combine benign operations, configuration errors, and vulnerability exploitation to achieve objectives…
-
Incomparable Minima in Agent Tool Authorization
arXiv cs.CR (Security)
arXiv:2610.31914v1 Announce Type: new Abstract: An agent that needs a tool needs authority to call it, and every proposal for governing that authority has to answer one question: of two grants that both let the agent finish a task, which…
-
Identity Amortization: Shared Resources and the Cost of Sybil Attacks
arXiv cs.CR (Security)
arXiv:2610.32685v1 Announce Type: new Abstract: Sybil defenses commonly price identities by requiring a resource for each one. When one resource can support several identities, an adversary can pay less per identity than the defense…
-
WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents
arXiv cs.CR (Security)
arXiv:2604.12284v2 Announce Type: replace Abstract: Web agents powered by vision-language models (VLMs) enable autonomous interaction with web environments by perceiving and acting on both visual and textual webpage content to accomplish…
-
EVSEFuzz : A Tool for Automated Testing of Protocol Implementations
arXiv cs.CR (Security)
arXiv:2610.32902v1 Announce Type: new Abstract: The rapid adoption and development of electric vehicle (EV) networks has required the expansive deployment of EV charging infrastructure (EVCI) which relies on communication protocols such as…
-
The Entire Quantum Computer on a Classical Leash
arXiv cs.CR (Security)
arXiv:2610.31775v1 Announce Type: cross Abstract: We show that a classical client with no quantum hardware can use a single untrusted and potentially malicious quantum server as if it were its own trusted quantum computer. Through the…
-
Memoir: Learning, Verifying, and Evolving False-Positive Memories for Static Application Security Testing Tools
arXiv cs.CR (Security)
arXiv:2608.09181v2 Announce Type: replace-cross Abstract: Static Application Security Testing (SAST) tools have become indispensable in modern secure software devel- opment. However, these tools often generate false-positive (FP) alerts…
-
Label-Budgeted Attribute Inference from Protected Features in Edge-Cloud Split Multimodal LLMs
arXiv cs.CR (Security)
arXiv:2610.32079v1 Announce Type: new Abstract: Edge-cloud split inference runs the early layers of a multimodal large language model (MLLM) on a device and sends intermediate features to a server to complete the task. While keeping raw…
-
Trusting the Tool: Asymmetric Deference of LLM Vulnerability Auditors to Static-Analysis Evidence
arXiv cs.CR (Security)
arXiv:2610.32876v1 Announce Type: cross Abstract: Pipelines that combine large language models (LLMs) with static analysis let the model consume the analyser's output as evidence, but whether the model distinguishes true from false…
-
Watermarking Should Be Treated as a Monitoring Primitive
arXiv cs.CR (Security)
arXiv:2605.13095v4 Announce Type: replace Abstract: Watermarking is a primary means for providers of generative models to meet legal requirements to mark synthetic content. A watermark embeds a hidden signal into generated content that a…
-
Agentic AI Defense: Decode-Time Provenance Binding for MCP
arXiv cs.CR (Security)
arXiv:2610.31974v1 Announce Type: new Abstract: Agentic AI systems using the Model Context Protocol (MCP) are vulnerable to indirect prompt injection through untrusted tool outputs. We demonstrate cross-modal trust laundering, in which…
-
Detecting Insecure Compositions of Clean Agent Skills via Capability-Flow Graph Analysis
arXiv cs.CR (Security)
arXiv:2610.32155v1 Announce Type: new Abstract: AI agents increasingly extend their capabilities by invoking third-party skills, where each skill encapsulates instructions, scripts, and resources for agents to execute on demand. This paper…
-
SEMPRE: Semantic-Aware Protocol Reverse Engineering via Consistency-Driven Joint Optimization
arXiv cs.CR (Security)
arXiv:2610.31844v1 Announce Type: new Abstract: Protocol reverse engineering (PRE) is essential for understanding undocumented or proprietary communication formats, enabling security-critical tasks such as vulnerability discovery, malware…
-
Block-A-Mole: The Sustainability Frontier of Moving-Target Censorship Resistance
arXiv cs.CR (Security)
arXiv:2606.08886v2 Announce Type: replace Abstract: Many censorship circumvention systems keep moving their servers to new cloud addresses, so that whatever the censor discovers soon goes stale. But clients often reach these servers…
-
On Task, Off Track: Benchmarking LLM and Agent Robustness to Near-Target Prompt Injection
arXiv cs.CR (Security)
arXiv:2610.32531v1 Announce Type: new Abstract: Prompt injection benchmarks assess whether large language models (LLMs) and agents resist malicious instructions embedded in external content. However, a system could perform well by…
-
SILMARILS-MV: Information-Theoretically Secure Multi-Verifier Signatures with Dealer-Free Key Issuance and Linear Aggregation for Permissioned Blockchains
arXiv cs.CR (Security)
arXiv:2610.31814v1 Announce Type: new Abstract: Permissioned blockchains authenticate transactions, votes and quorum certificates with computationally secure signatures, and post-quantum replacements inflate consensus traffic by orders of…
-
Fooling LLM Safety Guards into Judging the Wrong Text
arXiv cs.CR (Security)
arXiv:2610.31695v1 Announce Type: new Abstract: Safety guards check content before an LLM application acts on it, and most paste that content into a plain-text prompt. Content that imitates the prompt can append a second task, and the…
-
SynMark: Semantic-Coordinate Multi-Bit Watermarking during LLM Code Generation
arXiv cs.CR (Security)
arXiv:2610.32017v1 Announce Type: new Abstract: LLM-generated code is increasingly reused across downstream applications and often undergoes identifier renaming or structural refactoring, making robustness to functionality-preserving edits…
-
SPA: Structure-Preserving Approximation of Gated Activations under FHE
arXiv cs.CR (Security)
arXiv:2610.32065v1 Announce Type: new Abstract: Nonlinear activation evaluation remains a major bottleneck in neural inference under fully homomorphic encryption (FHE). FHE supports efficient addition and multiplication, but lacks native…
-
TRACE: Data-Free Text Reconstruction Attacks against Approximate Unlearning in LLMs
arXiv cs.CR (Security)
arXiv:2610.31995v1 Announce Type: new Abstract: As large language models (LLMs) face growing demands for data removal driven by regulatory compliance, copyright concerns, and privacy protection, approximate unlearning has emerged as a…
-
The 3DS Oracle: BIN Attack via the Network
arXiv cs.CR (Security)
arXiv:2610.32206v1 Announce Type: new Abstract: EMV 3-D Secure (3DS) requires a client-visible continuation boundary in browser-mediated flows; in some deployments, that boundary exposes a pre-authorization classification channel. This…
-
Tracing Money Laundering Across DeFi, Bridges, and Mixers on Ethereum
arXiv cs.CR (Security)
arXiv:2610.32210v1 Announce Type: new Abstract: Illicit actors exploit Ethereum's deep liquidity and diverse on-chain services to launder criminal proceeds by combining decentralized finance (DeFi) protocols, cross-chain bridges, and…
-
AgentTrace: Execution-Level Fingerprinting of Black-Box LLM Agents
arXiv cs.CR (Security)
arXiv:2610.32092v1 Announce Type: new Abstract: Verifying the provenance of autonomous LLM agents is a critical security challenge. Existing semantic attribution is easily obfuscated by system prompts, while active watermarking conflicts…
-
Privacy-Preserving Federated Loss Exploration for Vision-Based Perception under Non-IID Data
arXiv cs.CR (Security)
arXiv:2610.32626v1 Announce Type: new Abstract: Vision-based image classification models benefit from Federated Learning (FL) across vehicles, however learning accurate models from distributed vehicular cameras is challenging due to data…
-
AquaSense-ICS: A Hybrid Real-Simulated Cyber-Physical Dataset and Leakage-Aware Benchmark for Smart Water Quality Monitoring and Attack Detection
arXiv cs.CR (Security)
arXiv:2610.32661v1 Announce Type: new Abstract: Machine-learning research on water cyber-physical systems (CPS) is constrained by datasets that are either real but chemically poor, or simulated but free of sensing noise and attacks. We…
-
Beyond Copying: Lifelong Smart Contract Security Task Construction via Protocol Mutation
arXiv cs.CR (Security)
arXiv:2610.32453v1 Announce Type: new Abstract: AI agents can inspect code and run tests to support smart contract security. SlowMist reports about $38.6 billion in losses across the broader blockchain ecosystem. Existing evaluations can…
-
Developing Security Metrics for Automated Compliance Checking
arXiv cs.CR (Security)
arXiv:2610.32690v1 Announce Type: new Abstract: To automatically check for compliance with security-related standards, prose requirements must be translated to technical properties to make them measurable. A multitude of metrics have been…
-
DeepAVR: Deep Analysis via Multi-Agent Collaboration for Automated Vulnerability Repair
arXiv cs.CR (Security)
arXiv:2610.32345v1 Announce Type: cross Abstract: Automated Vulnerability Repair (AVR) has emerged as a critical defense against software security flaws, aiming to triage and fix bugs autonomously. Early LLM-based approaches focused on…
-
Constitution-Guided Watermarking
arXiv cs.CR (Security)
arXiv:2610.09552v2 Announce Type: replace Abstract: Regulation such as the EU AI Act requires providers of language models to mark generated text in a machine-readable way. Watermarking meets this requirement by embedding a secret-key…
-
Honeyquest for LLMs: Rethinking Cyber Deception for AI Attackers
arXiv cs.CR (Security)
arXiv:2606.21037v3 Announce Type: replace Abstract: The empirical foundation of cyber deception relies on human-centered hypotheses, but the rapid emergence of autonomous, AI-enabled attackers challenges whether this foundation transfers…
-
StealthRL: Reinforcement Learning Paraphrase Attacks for Multi-Detector Evasion of AI-Text Detectors
arXiv cs.CR (Security)
arXiv:2602.08934v3 Announce Type: replace-cross Abstract: AI-text detectors are increasingly used in high-stakes settings, but their robustness to meaning-preserving adversarial rewriting remains unclear. We introduce StealthRL, a…
-
WADE: An LSTM-Based Anomaly Detection Engine for WebAssembly Applications
arXiv cs.CR (Security)
arXiv:2610.31984v1 Announce Type: new Abstract: WebAssembly (Wasm) enables near-native performance for web applications through a portable and sandboxed execution model. However, its limited runtime protection mechanisms (e.g., the lack of…
-
LocalAlign: Enabling Generalizable Prompt Injection Defense via Generation of Near-Target Adversarial Examples for Alignment Training
arXiv cs.CR (Security)
arXiv:2605.01462v2 Announce Type: replace Abstract: Large language models are increasingly embedded into systems that interact with user data, retrieved web content, and external tools, creating a new attack surface: prompt injection…
-
Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models
arXiv cs.CR (Security)
arXiv:2610.10625v2 Announce Type: replace Abstract: Looped Language Models (LoopLMs) provide a parameter efficient approach to scaling model capabilities through repeated use of shared parameters across recurrent steps. Since each…
-
Embedding Large PQC KEMs in IKEv2
arXiv cs.CR (Security)
arXiv:2610.32356v1 Announce Type: new Abstract: Post-quantum key encapsulation mechanisms carry public keys far larger than the established VPN handshake protocol IKEv2 was designed for. At the same time, its initial exchange comprising…
-
ISC Stormcast For Monday, October 26th, 2026 https://isc.sans.edu/podcastdetail/10150, (Mon, Oct 26th)
SANS ISC