paperJuly 2026Unreviewed

Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks

Siyuan Li, Zehao Liu, Haoyu Li, Xi Lin, Ning Liu, Jun Wu, Jianhua Li, Mohsen Guizani

Abstract

As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reactive in nature. This limitation makes it difficult for them to counter sophisticated threats, as adversaries continuously adjust their strategies across multi-turn interactions. In this paper, we present a proactive defense framework for securing LLMs against evolving multi-turn adversarial attacks that combines disrup

Framework mappings

MITRE ATLAS

AML.T0043Craft Adversarial Data

Suggested from the entry's categories.

Cite

@misc{li2026stateful,
  title = {{Stateful Cooperative Agents Safeguarding LLMs Against Evolving Multi-Turn Attacks}},
  author = {Siyuan Li and Zehao Liu and Haoyu Li and Xi Lin and Ning Liu and Jun Wu and Jianhua Li and Mohsen Guizani},
  year = {2026},
  month = jul,
  eprint = {2608.00134},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2608.00134}
}