Latest news
-
AI Security via arXiv cs.CR
Certified Corruption Budgets: Anytime-Valid Leaderboard Claims under Adaptive Rigging
arXiv:2610.10597v1 Announce Type: new Abstract: Public leaderboards for AI models are read continuously, and attackers can see every published standing. Vote rigging…
-
AI Security via arXiv cs.CR
From Investigation Failures to Reliable SOC Agents: Understanding and Improving LLM-Based Alert Triage
arXiv:2610.10608v1 Announce Type: new Abstract: Security operations centers (SOCs) must triage large volumes of alerts, most of which are benign, while missed attacks…
-
Threat Intel via arXiv cs.CR
PyCache Trap: The Inspection-Execution Gap in Agent Skill Scanners
arXiv:2610.10612v1 Announce Type: new Abstract: Agent skills combine instructions with executable resources, giving third-party packages access to an agent's runtime…
-
Vulnerabilities via arXiv cs.CR
MRCert: Towards Post-deployment Patch Robustness Certification for Adversarially Patched Samples via Type-specific Masking
arXiv:2610.10617v1 Announce Type: new Abstract: In post-deployment time, inputs to deep learning models may or may not be adversarially patched. Patch robustness…
-
AI Security via arXiv cs.CR
When AI Finds Hidden Messages, Does It Report?
arXiv:2610.10620v1 Announce Type: new Abstract: When an assistant encounters a message for another AI, does it tell its user? Four fixed model-provider deployments…
-
AI Security via arXiv cs.CR
Safe at One Loop, Risky at Another: Aligning Safety Across Recurrent Depths in Looped Language Models
arXiv:2610.10625v1 Announce Type: new Abstract: Looped Language Models (LoopLMs) provide a parameter efficient approach to scaling model capabilities through repeated…
-
Vulnerabilities via arXiv cs.CR
SoK: Failure Modes in Common Criteria Product Evaluation - A Taxonomy and Design-for-Evaluability Guidance
arXiv:2610.10644v1 Announce Type: new Abstract: The Common Criteria (CC; ISO/IEC 15408) is the principal international framework for evaluating the security of IT…
-
AI Security via arXiv cs.CR
DITTO: A Context-aware Pickle-based Pre-Trained Model Scanner for Effective Security Audits
arXiv:2610.10735v1 Announce Type: new Abstract: Pre-trained models (PTMs) are widely distributed as serialized binaries, but their reuse often exposes software supply…
- Advertisement
-
AI Security via arXiv cs.CR
BRANCH: Bypassing Multi-Scanner AI Guardrails
arXiv:2610.10742v1 Announce Type: new Abstract: AI systems increasingly rely on Large Language Models (LLMs) as core reasoning engines, making them targets for prompt…
-
AI Security via arXiv cs.CR
Detection-Guided Adaptive Purification with Diffusion Models for Robust Audio Deepfake Detection
arXiv:2610.10752v1 Announce Type: new Abstract: Audio deepfake detectors remain vulnerable to adversarial perturbations that suppress the acoustic cues used for…
-
Vulnerabilities via arXiv cs.CR
CPU-Auth: Device Fingerprinting for Authentication via DVFS Side-Channel
arXiv:2610.10766v1 Announce Type: new Abstract: Lack of effective authentication has resulted in numerous security and privacy breaches, including unauthorized access to…
-
Vulnerabilities via arXiv cs.CR
When Flaws Cascade: Understanding Vulnerabilities and Exploitation Chains in JavaScript Engines
arXiv:2610.10844v1 Announce Type: new Abstract: JavaScript engines are pivotal to modern web browsers, enabling the execution of dynamic and interactive web…
-
AI Security via arXiv cs.CR
Power Side-Channel Membership Inference Attack on Embedded Machine Learning
arXiv:2610.10909v1 Announce Type: new Abstract: Membership inference attacks (MIAs) threaten the privacy of machine learning (ML) training data by determining whether a…
-
AI Security via arXiv cs.CR
Speedbumps: Rejection Attacks on Speculative Decoding
arXiv:2610.10929v1 Announce Type: new Abstract: Speculative decoding is a popular technique for increasing the speed and reducing the costs of large language model (LLM)…
-
AI Security via arXiv cs.CR
The Hint Weight of ML-DSA Signatures Is Key-Dependent: An Empirical Study across the Three FIPS 204 Parameter Sets
arXiv:2610.10992v1 Announce Type: new Abstract: Every ML-DSA (FIPS 204) signature carries a public hint vector h. We find that the Hamming weight of each hint polynomial…
-
AI Security via arXiv cs.CR
NOMOS: Compiling Written Policies into Statically Verified Tool-Call Gates for LLM Agents
arXiv:2610.11030v1 Announce Type: new Abstract: Tool-using LLM agents violate the policies they are deployed to enforce, often silently. Prior defenses hand-write rules…
-
Threat Intel via arXiv cs.CR
Accelerating HQC for Post-Quantum TLS 1.3 on x86 IoT Gateways
arXiv:2610.11107v1 Announce Type: new Abstract: Post-quantum TLS at an IoT gateway must protect many device connections without large increases in handshake delay, CPU…
-
AI Security via arXiv cs.CR
False Claims, Credible Images: A Red-Teaming Benchmark for Commercial Image Generators
arXiv:2610.11112v1 Announce Type: new Abstract: Image-generation models can now produce text-rich, natural-looking visual artifacts that are hard to distinguish from…
-
AI Security via arXiv cs.CR
Characterizing Statistical Separability in TP-CRIV for Probabilistic AI Models
arXiv:2610.11163v1 Announce Type: new Abstract: Third-party challenge-response identity verification (TP-CRIV) enables an independent verifier to assess whether a…
-
AI Security via arXiv cs.CR
BRACE: Differential Privacy for Dense Associative Memory with LSR Energy
arXiv:2610.11218v1 Announce Type: new Abstract: Dense associative memory (DAM) provides an energy-based framework for memory retrieval with close connections to…