1
SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks
论文揭示LLM存在位置性脆弱点，提出SlotGCG攻击方法，刷新越狱攻击成功率。
arXiv:2606.05609v1 Announce Type: cross Abstract: As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbre…