大模型对齐与安全

LeakSealer: A Semisupervised Defense for LLMs Against Prompt Injection and Leakage Attacks

Francesco Panebianco, Stefano Bonfanti, Francesco Trovò, Michele Carminati

机构 * Politecnico di Milano（米兰理工学院） 纠错

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

Comments 22 pages, preprint