Similar Items: Attention Is Where You Attack
- Pop Quiz Attack: Black-box Membership Inference Attacks Against Large Language Models
- You Snooze, You Lose: Automatic Safety Alignment Restoration through Neural Weight Translation
- Internet of Things Security: A Survey on Common Attacks
- GPUBreach: Privilege Escalation Attacks on GPUs using Rowhammer
- LoopTrap: Termination Poisoning Attacks on LLM Agents
- When Alignment Isn't Enough: Response-Path Attacks on LLM Agents