Similar Items: Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
- LoopTrap: Termination Poisoning Attacks on LLM Agents
- Secret Stealing Attacks on Local LLM Fine-Tuning through Supply-Chain Model Code Backdoors
- When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
- CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios
- Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
- Attention Is Where You Attack