Snyk VulnBench JS 1.0: Can LLMs Find the Same Bugs Twice?
Explorar
Noticias de IA
1359 elementos — filtrados, clasificados y sin duplicados
InstantForget: Update-Free Backdoor Unlearning with Inference-Time Feature Reset
MASCOT-Android: A Curated Dataset and Automated Collection Pipeline for Android Malware S…
Let Them Steal: Trapping Large Language Model Extraction Attacks with Knowledge Honeypot
CmdNeedle: Measuring the Incompleteness of Command Denylists for AI Agents
Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems
AutoDojo: Adaptive Attacks Expose Superficial Defenses and User-Underspecification Limits…
A Security Analysis of Long-Horizon Agentic AI Systems: Threats, Evaluation, and Framewor…
Phishing Email Detection Using Large Language Models
Reward Hacking in Language Model Agents: Revisiting AI Safety Gridworlds
Honeypot Protocol
Defending against Adaptive Prompt Injection Attacks via Reasoning-enabled Task Alignment
FragFuse: Bypassing Access Control of Large Language Model Agents via Memory-Based Query …
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Atta…
Microsoft shares new data on email security performance
What Is Anthropic’s Mythos AI and Why Was It Blocked?
Chainguard, Cyber Firms Use AI to Hunt for Open-Source Flaws
Safety-Contract Graph Multi-Agent Reinforcement Learning for Autonomous Network Security …
AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges
Rethinking Backdoor Adversarial Unlearning through the Lens of Catastrophic Forgetting in…
SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents
Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DECOM…
COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers
Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications
From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrails
Securing the Future of IoMT in the Post-Quantum Era: An Edge-Native Federated Learning Ap…
I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automo…
Same-Origin Policy for Agentic Browsers
Crypto Token’s 50% Wipeout Shows Magnitude of AI-Hacking Threat