AI Models Can Provably Hide Arbitrary Capabilities
Capability evaluations aim to surface dangerous model behaviors before deployment, but their reliability depends on the
2026-10-12 归档
今日共收录 1168 条安全情报，包含 403 个 CVE，452 篇安全通告，以及 67 篇研究论文。
← 返回归档列表Decision-Focused Learning for Cyber-Physical Risk-Aware Power Grid Operations
Power grid cyber-physical security requires intrusion detection methods that account for the operational consequences of
APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces
Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containi
A Systematic Study of Security Enforcement at Android Inter-Component Boundaries
Android's inter-process communication (IPC) mechanisms (Activities, Services, BroadcastReceivers, ContentProviders, and
Towards Safe World Models: Risks, Defenses, and Evaluation
World models support planning, control, learning from imagined experience, and model-mediated evaluation by predicting a
Secrets in Preamble: Practical and Robust PHY Information Hiding for Wi-Fi
Physical layer (PHY) information hiding refers to the concealment of secrets within PHY waveforms without compromising t
ECGWmark: Deep Watermarking for Electrocardiogram Signals
Secure transmission of electrocardiogram (ECG) signals remains a major challenge in telecardiology. While traditional ma
LETHE: Defending against Unauthorized Image-to-Video Generation via Value Diversity Collapse
Image-to-video (I2V) diffusion models can animate a single reference image into high-quality, subject-consistent videos,
Quantization-Tolerant Gradient Auditing for Active Inference-Attack Detection in Federated Learning
Inside a federated learning system a participant can quietly study the shared model and learn about others' private data
Understanding and Mitigating Cross-Session Attacks via Persistent Artifacts in Agent Skill Composition
Agent skills extend the capabilities of AI agents by bundling instructions, code, and resources into reusable packages.
The Limits of Query Monitoring against Distributed Model Extraction
Model providers now face distillation campaigns run through thousands of accounts, each of which looks like an ordinary
CAPE - Context-Aware Prioritization Engine for Vulnerability Scoring and Management
Vulnerability patching is critical for safeguarding an enterprise's software ecosystem from cyber attacks. However, patc
Space Over Statistic, Retraining Over Ranking: Auditing Training Labels Under Label-Only Backdoors
Some backdoor attacks never touch an image. FLIP only changes labels: on CIFAR-10, flipping 3% of them makes a ResNet-32
Provably Subexponential Algorithms for Bounded-Error LWE with Few Samples
We show that a variant of the Wagner/BKW-style algorithm for LWE of Kirchner and Fouque [KF15] solves decision and searc
WaveMark: Robust Wavelet-Domain Image Watermarking for Diffusion Models
Image watermarking enables provenance tracing for photorealistic images generated by diffusion models. However, state-of
AgentValve: Sybil-Resilient Payment Authorization for Permissionless AI Markets
AI agents increasingly select and pay service providers without human review. In emerging permissionless markets, howeve
Sample-Preserving Search-to-Decision Reduction for Noisy Linear Equations over Large Moduli
The Noisy Linear Equations problem involves finding the solution to a random linear system over a finite field given noi
The False Allure of "Security by Obscurity": A Game-Theoretic Approach
"Security by obscurity," or the idea that hiding how a system works helps protect it from adversaries, has long been poo
Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These
Power, Performance, and Area of HPC-Based Malware Detectors: An FPGA and Open-PDK ASIC Study
Hardware malware detectors (HMDs) classify programs as benign or malicious based on hardware performance counter (HPC) d