ICLR 2025 "llm security" Papers
3 papers found
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
Xiaogeng Liu, Peiran Li, G. Edward Suh et al.
ICLR 2025posterarXiv:2410.05295
106
citations
Can Watermarked LLMs be Identified by Users via Crafted Prompts?
Aiwei Liu, Sheng Guan, Yiming Liu et al.
ICLR 2025posterarXiv:2410.03168
12
citations
Persistent Pre-training Poisoning of LLMs
Yiming Zhang, Javier Rando, Ivan Evtimov et al.
ICLR 2025posterarXiv:2410.13722
34
citations