Tag: LLM security
Browse our exclusive articles!
Secure AI Agents: Defenses Against Indirect Prompt Attacks
Explore system-level defenses to protect AI agents from indirect prompt injection attacks and enhance their security and resilience.
Security Challenges in LLM-as-a-Judge Systems Explained
Explore key security risks and defenses in LLM-as-a-Judge systems with our comprehensive analysis and future research directions.
Robust Multilingual LLM Watermarking via Back-Translation
Discover how STEAM enhances multilingual LLM watermarking robustness across 100+ languages using back-translation and Bayesian optimization.
Boosting Jailbreak Attacks on LLMs Using Persona Prompts
Explore how persona prompts enhance jailbreak attacks on LLMs, revealing vulnerabilities and impacting AI safety with new genetic algorithm methods.
Claudini Unveils Advanced Adversarial Attacks for LLMs
Discover how Claudini's autoresearch pipeline finds cutting-edge adversarial attack algorithms, boosting AI security and outperforming existing methods.