SlotGCG: Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks

arXiv:2606.05609v1 Announce Type: cross Abstract: As large language models (LLMs) are widely deployed, identifying their vulnerability through jailbreak attacks becomes increasingly critical. Optimization-based attacks like Greedy Coordinate Gradient (GCG) have focused on inserting adversarial tokens to the end of prompts. However, GCG restricts...

Les hele artikkelen hos kilden.