Similar Items: Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
- FedAttr: Towards Privacy-preserving Client-Level Attribution in Federated LLM Fine-tuning
- LoopTrap: Termination Poisoning Attacks on LLM Agents
- When Alignment Isn't Enough: Response-Path Attacks on LLM Agents
- ARGUS: Defending LLM Agents Against Context-Aware Prompt Injection
- SkCC: Portable and Secure Skill Compilation for Cross-Framework LLM Agents
- CyBiasBench: Benchmarking Bias in LLM Agents for Cyber-Attack Scenarios