1
Bypassing Prompt Guards in Production with Controlled-Release Prompting
揭示LLM生产环境中提示防护的脆弱性，提出可控释放提示的新型攻击方法，为AI安全防护敲响警钟。
arXiv:2510.01529v3 Announce Type: replace Abstract: Ball et al. recently established that prompt filtering for AI alignment faces a fundamental barrie…