Tag: LLM security
Browse our exclusive articles!
Secret Stealing Attacks on Local LLM Fine-Tuning Backdoors
Discover how supply-chain model code backdoors enable secret stealing attacks on local LLM fine-tuning, threatening data privacy and security.
Threat Modeling for LLM-Enabled Robotic Systems Security
Explore holistic threat modeling of LLM-enabled robots, uncovering vulnerabilities and attack chains to enhance autonomous system safety.
Safety & Security Threats in AI Computer-Using Agents
Explore key safety and security threats of AI-driven computer-using agents and learn strategies to protect against emerging vulnerabilities.
Decision-Theoretic Steganography Detection in LLMs
Explore a novel decision-theoretic framework to detect, quantify, and mitigate steganography in large language models for enhanced AI oversight.
BlindGuard: Unsupervised Security for LLM Multi-Agent Systems
Discover BlindGuard, an unsupervised defense enhancing security in LLM-based multi-agent systems against unknown attacks without labeled data.