Cybersecurity
Cybersecurity news — Monday 19 October 2026
108 stories from 9 sources, every one in English. Each links to its publisher.
-
Nikkei discloses third data breach in a month, 1.8M records exposed
BleepingComputer
Nikkei Inc. disclosed a new data breach, the third in about a month, that exposed 1.83 million personal information records. [...]
-
WordPress SEO plugin Rank Math compromised to backdoor websites
BleepingComputer
Some downloads of the Rank Math PRO WordPress plugin from the vendor's official website carried malware that planted hidden backdoors in a supply-chain attack last week. [...]
-
Hackers hijack AOMEI update servers to secretly spread malware
BleepingComputer
Hackers reportedly compromised AOMEI's servers to distribute malware through a built-in promotional feature in its backup software, briefly tampering with configuration files before restoring them to their original state to hide the…
-
Bullhorn takes staffing platform offline to contain cyberattack
BleepingComputer
Staffing software company Bullhorn has disabled access to its platform to contain a cyberattack that caused a system-wide outage. [...]
-
Wyden seeks adoption of encryption tech at hundreds of federal agencies to protect visitors’ sensitive traffic
CyberScoop Asia
Hundreds of federal agencies should adopt an encryption tool to protect whistleblowers, veterans suffering from mental health crises and others from hackers who might target them when they reach out via agency websites, Sen. Ron Wyden said…
-
Siemens Software Center Vulnerability Exploited in ClickFix Malware Attacks
SecurityWeek
Attackers paired a genuine, signed copy of Siemens Software Center with malicious DLLs to infect Windows PCs via ClickFix lures. The post Siemens Software Center Vulnerability Exploited in ClickFix Malware Attacks appeared first on…
-
Hackers Exploit Plex2Shell Flaws to Install Crypto Miners and Linux Proxy Backdoor
The Hacker News
Threat actors have begun to exploit a chain of vulnerabilities in Plex Media Server to deploy cryptocurrency miners and reverse proxy software, a day after a proof-of-concept (PoC) went public. According to a researcher who goes by the…
-
OpenCode hack exposes API keys amid AI distillation attacks
BleepingComputer
The open-source AI coding project OpenCode has notified a small number of users that API keys they used with external providers were exposed in a security breach. [...]
-
How to find Flock cameras near you with MapQuest’s new ‘surveillance layer’
ZDNet Security
A name from the past is emerging again to help you stay out of sight of surveillance cameras.
-
Popular WordPress SEO Plugin Rank Math PRO Hijacked to Deliver Self-Restoring Backdoor
The Hacker News
Copies of Rank Math PRO, the paid version of the Rank Math SEO plugin for WordPress, that were downloaded from rankmath.com or delivered as updates between 20:02 UTC on October 15 and 07:12 UTC on October 16 contained malware, Rank Math…
-
Drupal Warns of Fast Exploitation Risk for Critical Core RCE Flaw
SecurityWeek
Critical flaws impact the Entity List and Field UI modules, and exploit paths exist with contributed modules. The post Drupal Warns of Fast Exploitation Risk for Critical Core RCE Flaw appeared first on SecurityWeek .
-
DHS to ban DeepSeek from federal civilian agencies
CyberScoop Asia
The Department of Homeland Security is banning the use of Chinese AI model DeepSeek and its affiliates by civilian federal agencies. The notice , set to publish Tuesday in the Federal Register, cites the Federal Acquisition Supply Chain…
-
Rank Math PRO WordPress Plugin Compromised in Supply Chain Attack
SecurityWeek
Hackers injected malware into Rank Math PRO version 3.0.123 packages distributed between October 15 and October 16. The post Rank Math PRO WordPress Plugin Compromised in Supply Chain Attack appeared first on SecurityWeek .
-
Microsoft fixes game, app crashes caused by recent Windows update
BleepingComputer
Microsoft has resolved a bug that caused games and apps using AC-3 (Dolby Digital) audio decoding to crash after installing the September 2026 Windows 11 preview update (KB5124010). [...]
-
AOMEI Backupper update servers hijacked to push malware: Check your PC
Malwarebytes Labs
The Google Threat Intelligence Group (GTIG) reports that attackers compromised AOMEI Technology’s update and notification infrastructure in a campaign investigated between April and July. AOMEI Backupper is backup software that the company…
-
⚡ Weekly Recap: 98 Zero-Days, Rogue AI Agents, $100M Crypto Theft, 700 Supermarkets Hit and More
The Hacker News
The worst problems don't always come with a warning. Sometimes they arrive through a service everyone trusts, a device someone bought, or a system nobody thought to check. By the time something looks wrong, the damage may already be done…
-
Inside the Underground Market for Know Your Client Services
BleepingComputer
Cybercriminals are selling forged identity documents, deepfake videos, and live verification services to help buyers bypass Know Your Client (KYC) checks. Flare examines how these underground services operate and the techniques used to…
-
F5 releases out-of-band patches for critical NGINX vulnerabilities
BleepingComputer
F5 has released out-of-band security patches to address multiple NGINX web server flaws, including three critical-severity vulnerabilities that can let attackers execute code on vulnerable systems. [...]
-
Feds Suspect Ransom Negotiator Ran ShinyHunters Extortion Site
Krebs on Security
U.S. federal investigators pursuing the ShinyHunters hacking group that recently stole highly sensitive data from the FBI have identified executives at two different ransomware negotiation firms who maintained unusually close relations…
-
ConnectWise Suspends Cloud Services in Response to Cyberattack
SecurityWeek
The services remain unavailable as the company continues remediation and security validation. The post ConnectWise Suspends Cloud Services in Response to Cyberattack appeared first on SecurityWeek .
-
GhostAction Attackers Plant Credential Stealer Disguised as Font in 94 GitHub Repositories
The Hacker News
The threat actor behind the GhostAction supply chain attack has expanded beyond injecting malicious GitHub Actions workflows into compromised projects to phish open-source developers and deliver a stealer malware disguised within a fake…
-
Microsoft fixes classic Outlook bug that hid Copilot buttons
BleepingComputer
Microsoft has fixed a known issue that removed the Copilot Chat and Copilot buttons in the classic Outlook desktop mail client for some Windows users. [...]
-
Plex2Shell Exploit Chain Weaponized Against Plex Servers Hours After Disclosure
SecurityWeek
Threat actors have been observed delivering cryptocurrency miners and proxy software. The post Plex2Shell Exploit Chain Weaponized Against Plex Servers Hours After Disclosure appeared first on SecurityWeek .
-
A sextortion conspiracy killed his son (Lock and Code S07E21)
Malwarebytes Labs
This week on the Lock and Code podcast… At just 17 years old, Jordan DeMay was murdered by strangers online. That’s how Jordan’s father, John DeMay, described what happened to his son four years ago. At home in Michigan, Jordan was…
-
One Compromised Login Exposed Millions of California Students’ Records
SecurityWeek
Intruders used compromised credentials to access an ETS SFTP server, copying records of California students back to 2006. The post One Compromised Login Exposed Millions of California Students’ Records appeared first on SecurityWeek .
-
From Email-to-Case to the Boardroom: How Inherited Agents Break Governance Built for Software
The Hacker News
In Salesforce Agentforce, the recommended way to make an agent respond to events is a Flow: a record is created or a case is updated, and the Flow passes data into the agent's prompt. Separately, Email-to-Case and Web-to-Case turn inbound…
-
Exploited Fortinet Bug Linked to Stealthy FortiGate Implant in Telecom Hack
SecurityWeek
The persistent, stealthy FortiGate implant was deployed against a telecommunications organization. The post Exploited Fortinet Bug Linked to Stealthy FortiGate Implant in Telecom Hack appeared first on SecurityWeek .
-
Millions of California students’ sensitive data stolen in breach
Malwarebytes Labs
Personal information belonging to millions of current and former California public school students has been stolen from a system operated by Educational Testing Service (ETS). ETS is a nonprofit organization that helps run the state’s…
-
Training AIs to Solve CAPTCHAs
Schneier on Security
Interesting research : Abstract : Vision-language models (VLMs) can solve visual CAPTCHAs without task-specific training, but the agents built on them approach every challenge from scratch. For such an agent, the hundredth instance of a…
-
Fake Web3 Accelerator Uses npm Packages to Spread Malware and Hijack AI Agent Traffic
The Hacker News
A fake Web3 accelerator has been observed pushing information stealers and backdoors to Windows and macOS systems using malicious npm packages under the pretext of offering free artificial intelligence (AI) credits for Anthropic Claude and…
-
Spyware found on devices belonging to prominent Serbian critics as elections loom
CyberScoop Asia
Spyware has been detected on devices used by some of Serbia’s most prominent figures connected to the country’s political upheaval, according to researchers who announced their findings Monday. Vladan Ðokić, the rector of the University of…
-
MITRE ATT＆CK v20 Catalogs AI Abuse, MFA Bypass, Water Utility Attacks
SecurityWeek
Defenders get 15 new detection strategies, six for Enterprise and nine for ICS, backed by 38 analytics. The post MITRE ATT&CK v20 Catalogs AI Abuse, MFA Bypass, Water Utility Attacks appeared first on SecurityWeek .
-
Microsoft: October Windows Server updates break Exchange sign-in, mail flow
BleepingComputer
Microsoft has confirmed that this month's Windows Server security updates are causing OWA sign-in and mail delivery issues on some Exchange Server systems. [...]
-
Anthropic Acquires Confidential AI Startup Opaque Systems
SecurityWeek
Opaque Systems has developed technology that lets AI systems use sensitive data while keeping it protected by the underlying hardware. The post Anthropic Acquires Confidential AI Startup Opaque Systems appeared first on SecurityWeek .
-
A week in security (October 12 – October 18)
Malwarebytes Labs
Last week on Malwarebytes Labs: Eiliko robot companion exposes private chats and can be hijacked “Spray and pray” job applications could make it harder for you to spot a scam OpenAI sued over children safety and data use Update Chrome…
-
Unpatched Broadcom Wi-Fi Flaw Lets Attackers in Range Run Code as Root on Routers
The Hacker News
A flaw in Broadcom's Wi-Fi setup software lets an attacker within radio range run code as root on Broadcom-based routers, without the network password or any pairing step, security researcher Quentin Kaiser disclosed on October 16. He…
-
OpenCode Console Breach May Have Exposed OpenAI, Anthropic, and Google API Keys
The Hacker News
An intruder reached a legacy system at OpenCode on the night of October 16 and may have exposed the third-party AI provider keys that users had saved in OpenCode Console, the company said. Console is OpenCode's optional hosted service: a…
-
Recoverability-Controlled Safety Miscalibration in Large Language Models
arXiv cs.CR (Security)
arXiv:2610.22425v1 Announce Type: new Abstract: Safety-aligned language models are expected to refuse harmful requests while remaining useful for benign ones. However, because many evaluations score only the final response, they often…
-
Actions with Receipts: Jointly Binding Claims, Evidence, and Execution for Replayable Tool-Agent Auditing
arXiv cs.CR (Security)
arXiv:2610.00327v2 Announce Type: replace Abstract: Tool-using agents can expose citations and execution logs while leaving a critical association unaudited: whether the claim shown to a user is the claim emitted by the committed execution…
-
SAFE-Mem: Secure Agentic Memory with Fine-Grained Authority and Governance-Aware Retrieval
arXiv cs.CR (Security)
arXiv:2610.22959v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on persistent memory to support long-term reasoning and personalized interactions. However, information collected from external sources can…
-
TUPLE-Bench: Evaluating and Mitigating Privacy-Utility Trade-offs in Typed Decision Models
arXiv cs.CR (Security)
arXiv:2610.23668v1 Announce Type: new Abstract: Typed decision models often return more than a selected category. They also expose probabilities for each candidate and, sometimes, a separate confidence score. These fields support…
-
VulnSAGE: Adjudicating SAST Reports by Connecting LLM Reasoning to Program Structure
arXiv cs.CR (Security)
arXiv:2610.23035v1 Announce Type: cross Abstract: Static Application Security Testing (SAST) reports flag operations whose safety depends on project-specific context, and maintainers must decide which reports describe real defects. Large…
-
ECHO: Replacing the Compliance Proxy with Response Harmfulness in Optimization-Based Jailbreak Attack
arXiv cs.CR (Security)
arXiv:2610.23030v1 Announce Type: new Abstract: Despite extensive safety alignment, large language models remain vulnerable to jailbreak attacks. Existing optimization-based attacks share a single objective: maximize a token-level proxy of…
-
Towards Hyperparameter Transfer for Differentially Private Optimization
arXiv cs.CR (Security)
arXiv:2610.22976v1 Announce Type: cross Abstract: Scaling laws and hyperparameter tuning remain central challenges in training large-scale models, particularly under differential privacy (DP), where optimization is further complicated by…
-
SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing
arXiv cs.CR (Security)
arXiv:2605.29468v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used to support scientific work, but it is unclear whether they uphold responsible conduct of research (RCR) norms or help undermine them. We…
-
When Approval Becomes Execution: Authorization-Grounded Workflow Attacks on Tool-Using Agents
arXiv cs.CR (Security)
arXiv:2610.23077v1 Announce Type: new Abstract: Tool-using language-model agents increasingly rely on local services for document access, approval management, and enterprise workflow execution. This paper studies an authorization-grounded…
-
AgentLoupe: Kernel-Resident Semantic Causal Labels for AI Agent Observability
arXiv cs.CR (Security)
arXiv:2610.23233v1 Announce Type: new Abstract: AI agents translate user intents into system actions via tool invocations. Accurately attributing these actions to their originating LLM interactions is essential for security auditing, yet…
-
Token-Level Attribution of Multi-Mode LLM Watermarks: Optimal Rule and Belief Weighting
arXiv cs.CR (Security)
arXiv:2610.23601v1 Announce Type: new Abstract: A watermark verifier may hold many modes, i.e., secret keys, and a document may mix spans of different modes with unwatermarked text. Directly reporting the mode with the largest pivotal…
-
Concrete Functions in Private Simultaneous Quantum Messages: Quantum Advantages and Structural Limitations
arXiv cs.CR (Security)
arXiv:2610.23090v1 Announce Type: cross Abstract: Private simultaneous quantum messages (PSQM) provide a minimal model of noninteractive secure multiparty quantum computation, yet their communication complexity for concrete functions…
-
Erase the Mark, Preserve the Motion: Temporally Consistent Removal of Video Watermarks
arXiv cs.CR (Security)
arXiv:2610.22457v1 Announce Type: new Abstract: Recent advances in video generation have increased the demand for reliable watermarking for copyright protection, yet the robustness of video watermarks against removal attacks remains…
-
The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems
arXiv cs.CR (Security)
arXiv:2610.22722v1 Announce Type: new Abstract: Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconstruct text from these messages. Comparing privacy evaluations is…
-
Harnessing Trust in Directed Graphs: Redefining Robustness of Graph Learning
arXiv cs.CR (Security)
arXiv:2306.02002v2 Announce Type: replace-cross Abstract: Existing research on robust Graph Neural Networks (GNNs) focuses predominantly on undirected graphs, overlooking the trustworthiness inherent in the link directions of directed…
-
VStress: Correlation-Aware Auditing and Adaptive Budget Allocation for Repeated Verifiers
arXiv cs.CR (Security)
arXiv:2609.36958v2 Announce Type: replace-cross Abstract: Repeated verifier calls are useful only when they contribute conditional information. We introduce VStress, an auditable replay contract, and VStress-CA, a correlation-aware…
-
Surprise Masking: Private Data Filtering with Model Likelihoods
arXiv cs.CR (Security)
arXiv:2610.22988v1 Announce Type: new Abstract: Data useful for language model (LM) training can contain private or unwanted information that is at risk of being learned or memorized. We propose Surprise Masking (SM), a simple form of…
-
Can SOLARBURST go silicon? A systematic analysis on software supply chain attacks for VLSI design flows
arXiv cs.CR (Security)
arXiv:2610.22580v1 Announce Type: new Abstract: An attacker targeting the software supply chain (SWSC) of VLSI tools can fully subvert the VLSI design pipeline through purely software level compromises. However, cur- rent literature on…
-
BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM Partition
arXiv cs.CR (Security)
arXiv:2610.21565v2 Announce Type: replace Abstract: On-device deployment of large language models (LLMs) is increasingly adopted due to latency and privacy requirements, but exposes proprietary models to reverse engineering and…
-
Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems
arXiv cs.CR (Security)
arXiv:2311.11796v3 Announce Type: replace Abstract: Transferable attacks allow adversarial manipulations or learned attack mechanisms constructed in one setting to compromise other AI systems, potentially reducing attack costs and…
-
A Gradient-Optimized TSK Fuzzy Framework for Explainable Phishing Detection
arXiv cs.CR (Security)
arXiv:2504.18636v2 Announce Type: replace Abstract: Phishing attacks represent an increasingly sophisticated and pervasive threat to individuals and organizations, causing significant financial losses, identity theft, and severe damage to…
-
Exploring The Empirical Privacy Landscape of Synthetic Data
arXiv cs.CR (Security)
arXiv:2610.22659v1 Announce Type: new Abstract: Methods for training language models on sensitive data differ in how they balance capability gains against the risk of leaking private information. In this paper, we present a controlled…
-
From Billion-Scale to Million-Scale Language Models: Operational Capabilities for Embedded Post-Exploitation
arXiv cs.CR (Security)
arXiv:2610.23534v1 Announce Type: new Abstract: Small Language Models (SLMs) are increasingly attractive for resource-constrained environments due to their low computational footprint. These characteristics also make them candidates for…
-
Agenra: A Language and Verified Core for Stateful LLM Agent Authorization
arXiv cs.CR (Security)
arXiv:2608.22868v2 Announce Type: replace Abstract: Applications that deploy LLM agents keep revising the permissions their agents use. When authority is consumable, even widening a permission can break a legitimate workflow, because an…
-
GRAD: Graph-Structured Antibody Defense for LLM Agents
arXiv cs.CR (Security)
arXiv:2610.22828v1 Announce Type: new Abstract: Memory poisoning and decomposition attacks distribute malicious evidence across the operations of large language model agents. Existing request-level defenses can miss such attacks because…
-
Aspire: Practical Batch Queries on Dynamic Encrypted Database with Full Leakage Suppression
arXiv cs.CR (Security)
arXiv:2610.23057v1 Announce Type: new Abstract: Leakage-abuse attacks against encrypted database systems exploit semantic leakage and pose a severe threat to the confidentiality of plaintext data and queries. To address this problem, we…
-
Cryptographically Secure Agent-to-Agent Communication in Multi-Agent Systems
arXiv cs.CR (Security)
arXiv:2610.23078v1 Announce Type: new Abstract: Multi-agent systems (MAS) comprise AI agents that collaborate or compete to perform complex, distributed tasks. Their dynamic interactions create opportunities for threat actors to target and…
-
ACE: An AI-Orchestrated Intrusion Detection and Compliance Mapping Engine
arXiv cs.CR (Security)
arXiv:2610.22702v1 Announce Type: new Abstract: This study proposes the Automated Compliance Engine (ACE), an AI-orchestrated framework that links intrusion detection, regulatory control mapping, and automated countermeasure deployment for…
-
RAMP: Toward Ubiquitous Quantum-Safe Key Distribution as a Service
arXiv cs.CR (Security)
arXiv:2610.22879v1 Announce Type: new Abstract: Quantum key distribution (QKD) offers a security foundation independent of computational hardness assumptions. However, its reliance on specialized hardware limits access by ordinary users…
-
How Agents Ask for Permission: User Permissions for AI Agents, from Interfaces to Enforcement
arXiv cs.CR (Security)
arXiv:2607.13718v3 Announce Type: replace Abstract: As AI agents grow in prevalence, so too do their risks to users, creating a need for robust and usable systems for agent permissions. Many recent proposals implement product-level…
-
Identify, Classify, Act: Per-Instruction Controlled Compliance for LLMs over External Data
arXiv cs.CR (Security)
arXiv:2610.22874v1 Announce Type: cross Abstract: LLMs over external data face a per-instruction tension: a single document or tool return often interleaves legitimate directives with adversarial prompt injections, and the model must…
-
Trojan Horse: Automated Repository Poisoning against Coding Agents
arXiv cs.CR (Security)
arXiv:2610.23109v1 Announce Type: new Abstract: Coding agents are increasingly capable with autonomy, which exposes them to repository-level poisoning. Existing red-teaming studies remain restricted to manual selection for malicious…
-
Practical and Private Hybrid ML Inference with Fully Homomorphic Encryption
arXiv cs.CR (Security)
arXiv:2509.01253v2 Announce Type: replace Abstract: In contemporary cloud-based services, protecting users' sensitive data and ensuring the confidentiality of the server's model are critical. Fully homomorphic encryption (FHE) enables…
-
Sharing is caring: Attestable and Trusted Workflows out of Distrustful Components
arXiv cs.CR (Security)
arXiv:2603.03403v3 Announce Type: replace Abstract: Trusted Execution Environments (TEEs) protect private memory and attest initial code and configuration, but neither constrain nor attest shared channels between TEEs or with the untrusted…
-
An Agentic ENF Framework for Forensic Video Authentication Against Generative AI
arXiv cs.CR (Security)
arXiv:2610.22440v1 Announce Type: new Abstract: Generative models now synthesise video that is hard to distinguish from genuine footage, and learned detectors that key on a generator's artefacts degrade sharply on unseen models. This paper…
-
Model-as-a-Trojan: Self-Activating Covert DNS Exfiltration Baked Into the Weights of an LLM Agent
arXiv cs.CR (Security)
arXiv:2610.22578v1 Announce Type: new Abstract: Open-weight models are downloaded from public hubs and run inside agent harnesses that grant them tools, most powerfully, a shell, under the assumption that a sandbox contains whatever the…
-
Veil-Then-Reveal: Protecting PII Privacy via Reversible Pseudo-Anonymization in Zero-Trust User--LLM Interaction
arXiv cs.CR (Security)
arXiv:2610.22800v1 Announce Type: new Abstract: Large language models (LLMs) increasingly process sensitive documents and personal information, yet sending prompts containing personally identifiable information (PII) to remote providers…
-
Provable Authority: A Protocol for Verifiable Authority Resolution and Control Across Human, Organizational, and Agentic Transactions
arXiv cs.CR (Security)
arXiv:2610.22899v1 Announce Type: new Abstract: Payment systems authenticate users, devices, accounts, and cryptographic credentials, but a relying party, such as a counterparty, payment rail, marketplace, or autonomous agent runtime…
-
Provable Compliance: A Protocol for Runtime Compliance Evidence and Transaction-Specific Decisioning
arXiv cs.CR (Security)
arXiv:2610.22913v1 Announce Type: new Abstract: Regulated institutions already perform onboarding, screening, monitoring, and review, but compliance evidence ages, and whether it supports a decision depends on the institution, product…
-
MobileJailBench: Red Queen Jailbreak Benchmarking for Mobile Agents
arXiv cs.CR (Security)
arXiv:2610.23303v1 Announce Type: new Abstract: MLLM-based mobile agents are rapidly gaining autonomy in perception, planning, and closed-loop execution in dynamic mobile environments. However, this autonomy also broadens the attack…
-
On the (In)stability of Adaptive Fee Mechanisms in Multi-Chain Systems
arXiv cs.CR (Security)
arXiv:2610.23305v1 Announce Type: new Abstract: EIP-1559 has become the dominant transaction fee mechanism in permissionless blockchains, regulating scarce block space through an adaptive base fee. The design balances a trade-off between…
-
MobileInject: Evaluating Reasoning-to-Action Security of MLLM-Based Mobile Agents under Cross-Modal Consistency Injection
arXiv cs.CR (Security)
arXiv:2610.23307v1 Announce Type: new Abstract: Multimodal large language model (MLLM)-based mobile agents are rapidly evolving from conversational assistants into autonomous systems that perceive, reason over, and act on smartphone…
-
ABF-Bench: A Verifiable Benchmark for Agentic Blockchain Forensics
arXiv cs.CR (Security)
arXiv:2610.23656v1 Announce Type: new Abstract: Blockchain forensics is adversarial and open-ended: money launderers split, swap, and bridge funds, cut their trail at mixers or custodial services, and change tactics from one incident to…
-
HardEval: An Execution-Verified Benchmark for AI-Driven Security Hardening and Compliance Remediation
arXiv cs.CR (Security)
arXiv:2610.23685v1 Announce Type: new Abstract: Implementing Security Technical Implementation Guide (STIG) controls remains a demanding operating-system administration task. Each natural-language security requirement must be translated…
-
Monitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework Boundaries
arXiv cs.CR (Security)
arXiv:2610.23362v1 Announce Type: cross Abstract: Modern LLM applications rely on runtime monitors that inspect tool calls, traces, streams, detector outputs, and verifier inputs. This creates an interface-reliability problem: a framework…
-
Bad Diagnosis: Analyzing Consent and Data Collection Practices of Mobile Medical Apps
arXiv cs.CR (Security)
arXiv:2610.23851v1 Announce Type: cross Abstract: Mobile health (mHealth) apps collect personally-identifiable information while handling uniquely sensitive medical data, ranging from mental health records to real-time glucose or heart…
-
OTS-PC: OTS-based Payment Channels for the Lightning Network
arXiv cs.CR (Security)
arXiv:2511.04021v3 Announce Type: replace Abstract: We present a new type of bidirectional payment channel based on One-Time Signatures on state sequence numbers. This new construction is simpler than the Poon-Dryja construction, but…
-
The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code
arXiv cs.CR (Security)
arXiv:2605.03619v3 Announce Type: replace Abstract: Malware authors traditionally rely on polymorphic techniques to produce variants within a malware family, complicating detection. Generative AI enables attackers to automatically…
-
CT0: Cybersecurity Transformer
arXiv cs.CR (Security)
arXiv:2610.16550v2 Announce Type: replace Abstract: General-purpose frontier models are large, expensive to run, and increasingly reluctant to engage with authorised defensive- and offensive-security work. We ask the opposite question: how…
-
Task-aware Kernel Stein certificates for R\'{e}nyi differential privacy
arXiv cs.CR (Security)
arXiv:2610.23798v1 Announce Type: cross Abstract: R\`enyi differential privacy, based on R\`enyi divergence, has become a notion of choice for privacy guarantees. However, outside the Gaussian setting, R\`enyi divergence can be difficult…
-
CHAMP: Cayley HAshing with Matrix Products
arXiv cs.CR (Security)
arXiv:2610.04442v2 Announce Type: replace Abstract: Cayley hash functions hash binary strings by representing the bits of the message as elements of a semigroup and multiplying the corresponding elements. This gives Cayley hash functions…
-
Capability-Gated Language Models: Security Composes, Utility Does Not
arXiv cs.CR (Security)
arXiv:2609.00445v3 Announce Type: replace Abstract: Deployed language model safeguards (safety fine-tuning, filtering, unlearning) vary by principal only outside the model weights: filters are reconfigured, tiers are multiplied, and…
-
Ignored, Not Refused: What Low Prompt-Injection Success Rates Hide in Small Tool-Using Agents
arXiv cs.CR (Security)
arXiv:2610.23254v1 Announce Type: cross Abstract: Tool-using agents read untrusted external content, which exposes them to indirect prompt injection (IPI), where hidden instructions hijack the agent's tool calls. Benchmarks measure IPI…
-
A Deeper Dive into the Irreversibility of PolyProtect: Making Protected Face Templates Harder to Invert
arXiv cs.CR (Security)
arXiv:2605.03857v2 Announce Type: replace-cross Abstract: This work presents a deeper analysis of the "irreversibility" property of PolyProtect, a biometric template protection method initially proposed for securing face embeddings…
-
When Core-Network Elements Become Reachable: Field-Level Exploitability Analysis in Diameter
arXiv cs.CR (Security)
arXiv:2610.22943v1 Announce Type: new Abstract: The increasing exposure of cellular core-network elements to public networks has turned Diameter signaling interfaces into a practical attack surface. While large language models (LLMs) show…
-
Capital Costs Protect the Network: Mining Gap Dynamics in Proof-of-Work Blockchains Under a Stochastic Mempool
arXiv cs.CR (Security)
arXiv:2610.22451v1 Announce Type: new Abstract: Proof-of-Work blockchains increasingly rely on transaction fees to keep miners engaged as block subsidies decline. An immediate outcome of this is that miners may sit idle at the start of a…
-
Stealthy Poisoning Attacks via Reused KV Cache of Reasoning
arXiv cs.CR (Security)
arXiv:2610.22873v1 Announce Type: new Abstract: Modern large language model (LLM) systems reuse key-value (KV) caches to accelerate inference. Recent work has shown that reusing KV caches from reasoning traces can also improve task…
-
CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades
arXiv cs.CR (Security)
arXiv:2610.20668v2 Announce Type: replace Abstract: We introduce CascadeLedger, a counterfactual execution-audit framework for budgeted language-model cascades. The protocol enforces call-before-read semantics, binds successful reads to…
-
Rethinking Quality in Large Language Model Routing: Security-Conditioned Model-and-Budget Selection
arXiv cs.CR (Security)
arXiv:2610.18566v2 Announce Type: replace-cross Abstract: Large language model (LLM) routers reduce serving cost by choosing which model to call and how many output tokens to grant it for each query. Existing routers rank model-budget…
-
Auditable and Transparent Fully Authenticated Disk Encryption via USB Storage Interposition
arXiv cs.CR (Security)
arXiv:2607.12716v2 Announce Type: replace Abstract: Full Disk Encryption (FDE) has become increasingly important in the last decades due to the evident confidentiality concerns. In most systems, encryption is provided by an operating…
-
StratFL: Countering Covert Model Poisoning Attacks with Strategic Federated Learning
arXiv cs.CR (Security)
arXiv:2610.22626v1 Announce Type: new Abstract: Advanced persistent threats (APTs) are a major concern in federated learning (FL) deployments in critical sectors such as healthcare, and finance. Traditional defense mechanisms fail to…
-
Everyone's a little bit racist: a novel ML backdoor attack in black-box mode
arXiv cs.CR (Security)
arXiv:2610.22459v1 Announce Type: new Abstract: Backdoors are among the most impactful attacks against Machine Learning (ML), yet most existing methods assume some form of training-time poisoning or direct model manipulation. This is often…
-
RedDarwin: Evolving Jailbreak Skills against Frontier LLMs
arXiv cs.CR (Security)
arXiv:2610.23726v1 Announce Type: new Abstract: Red teaming must continually adapt as frontier LLM safeguards evolve, yet existing approaches largely search for adversarial prompts or optimize within fixed attack procedures. We observe…
-
Watermarkability: Measuring and Improving Language-Model Compatibility with Logit-Based Watermarks
arXiv cs.CR (Security)
arXiv:2610.22810v1 Announce Type: cross Abstract: Language-model watermarks can help identify model-generated text, encode provenance information, and detect post-generation edits. A broad class of logit-based watermarks increases the…
-
From GAN-Based Models to GPT-5: A Taxonomy-Guided Study of Human Performance in Detecting Deepfake Face Images
arXiv cs.CR (Security)
arXiv:2610.23144v1 Announce Type: cross Abstract: Generative models for deepfakes have rapidly evolved from GAN-based architectures to diffusion models and multimodal large language models (MLLMs). However, empirical research on human…
-
An AI Approach to Verified Production Cryptographic Libraries
arXiv cs.CR (Security)
arXiv:2608.00965v2 Announce Type: replace Abstract: Cryptographic code is critical infrastructure that must be correct, yet formally verifying production libraries remains difficult. Existing language-model proof systems solve isolated…
-
What It Is, Not What It Says: Securing Agentic Browsing Interactions with Web Semantics
arXiv cs.CR (Security)
arXiv:2610.22697v1 Announce Type: new Abstract: AI agents increasingly browse the web on users' behalf, yet they consume webpages as screenshots or text, exposing their LLMs to unvetted third-party content. Browsers enforce semantics under…
-
Broad and Efficient PII Detection with Unified Labels
arXiv cs.CR (Security)
arXiv:2610.22597v1 Announce Type: cross Abstract: Personally Identifiable Information (PII) detection models must efficiently find identifiers across diverse contexts while maintaining a low false-positive rate (FPR) on high-volume…
-
Evidence-Bound Gateway-Path Provenance for Third-Party LLM Inference
arXiv cs.CR (Security)
arXiv:2606.22560v2 Announce Type: replace Abstract: Third-party LLM gateways select providers, models, endpoints, and fallback paths while also authoring the records used to explain and bill those decisions. We present evidence-bound…
-
Every Model Cheats: Prompt-Level Mitigation of Cheating on Offensive Cyber Tasks
arXiv cs.CR (Security)
arXiv:2607.21763v2 Announce Type: replace Abstract: Large language model (LLM) agents routinely cheat on cybersecurity benchmarks, inflating reported pass rates far beyond genuine capability. Prior audits of Cybench found cheating in…
-
Exponentially Fewer-Server PIR from Sparser $S$-Decoding Polynomials
arXiv cs.CR (Security)
arXiv:2607.22033v2 Announce Type: replace-cross Abstract: We show that under a plausible number-theoretic conjecture, for any constant $s$ there exists an $s$-server private information retrieval (PIR) protocol that on an $n$-bit database…