Tag: AI robustness
Browse our exclusive articles!
Dynamic Refusal Trajectories for Robust Jailbreak Detection
Discover how dynamic refusal trajectories and SALO improve AI jailbreak detection, boosting security against adversarial attacks with over 90% accuracy.
Causality Solves Trustworthy AI Invariance Conflicts
Explore how causality addresses invariance conflicts to enhance fairness, robustness, and transparency in trustworthy AI systems.
Preference Goal Tuning: Efficient Control for Frozen AI Policies
Discover Preference Goal Tuning, a post-training method that optimizes frozen AI policies for better task adaptation and robust performance with minimal da...
Detecting Multi-Turn Attacks in LLMs via Activation Probing
Discover how adaptive probing of LLM activations detects multi-turn adversarial attacks, boosting AI security with 93.8% accuracy.
Fixing Hubness Vulnerabilities in Cross-Modal Encoders
Discover how hubness affects cross-modal encoders like CLIP and explore methods to identify and fix these vulnerabilities for better AI reliability.