Similar Items: When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
- LoopTrap: Termination Poisoning Attacks on LLM Agents
- CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
- STARE: Step-wise Temporal Alignment and Red-teaming Engine for Multi-modal Toxicity Attack
- Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
- Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
- Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents