DATABANK

Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks

Rana Muhammad Shahroz Khan, Zhen Tan, Sukwon Yun, Charles Fleming, Tianlong Chen

papercode

prompt injection

Cite this paper

Credit the original research and its authors.

BibTeX
@misc{khan-2025-agents-under-siege,
  author = {Rana Muhammad Shahroz Khan and Zhen Tan and Sukwon Yun and Charles Fleming and Tianlong Chen},
  title = {{Agents Under Siege: Breaking Pragmatic Multi-Agent LLM Systems with Optimized Prompt Attacks}},
  year = {2025},
  note = {ACL 2025},
  url = {https://arxiv.org/abs/2504.00218}
}