大模型对齐与安全

RL Is a Hammer and LLMs Are Nails: A Simple Reinforcement Learning Recipe for Strong Prompt Injection

Yuxin Wen, Arman Zharmagambetov, Ivan Evtimov, Narine Kokhlikyan, Tom Goldstein, Kamalika Chaudhuri, Chuan Guo

机构 * University of Maryland（马里兰大学） ； FAIR at Meta（Meta 元宇宙研究院） 纠错

专题命中 提示注入 ：prompt injection(title,abstract)；safety(abstract)；分类 cs.LG

AgentTypo: Adaptive Typographic Prompt Injection Attacks against Black-box Multimodal Agents

Yanjie Li, Yiming Cao, Dong Wang, Bin Xiao

机构 * Computing Department of Hong Kong Polytechnic University（香港理工大学计算机系） ； Computing Department, The Hong Kong Polytechnic University（香港理工大学计算机系） 纠错

专题命中 提示注入 ：prompt injection(title,abstract)；分类 cs.AI

Comments 13 pages, 8 figures. Submitted to IEEE Transactions on Information Forensics & Security

VortexPIA: Indirect Prompt Injection Attack against LLMs for Efficient Extraction of User Privacy

Yu Cui, Sicheng Pan, Yifei Liu, Haibin Zhang, Cong Zuo

专题命中 提示注入 ：prompt injection(title,abstract)

Backdoor-Powered Prompt Injection Attacks Nullify Defense Methods

Yulin Chen, Haoran Li, Yuan Sui, Yangqiu Song, Bryan Hooi

专题命中 提示注入 ：prompt injection(title,abstract)

Comments EMNLP 2025 Findings

TopicAttack: An Indirect Prompt Injection Attack via Topic Transition

Yulin Chen, Haoran Li, Yuexin Li, Yue Liu, Yangqiu Song, Bryan Hooi

专题命中 提示注入 ：prompt injection(title,abstract)

Comments EMNLP 2025

Can Indirect Prompt Injection Attacks Be Detected and Removed?

Yulin Chen, Haoran Li, Yuan Sui, Yufei He, Yue Liu, Yangqiu Song, Bryan Hooi

专题命中 提示注入 ：prompt injection(title,abstract)

Comments ACL 2025 Main