作者位次 #3/4ICLR 2026Poster· Social Aspects / Privacy-preserving Statistics and Machine Learning
FHE-Coder: Benchmarking Secure Agentic Code Generation for Fully Homomorphic Encryption
Mayank Kumar · Jiaqi Xue · Mengxin Zheng · Qian Lou
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Mayank Kumar · Jiaqi Xue · Mengxin Zheng · Qian Lou
Yifei Zhao · Qian Lou · Mengxin Zheng
Nokimul Hasan Arif · Qian Lou · Mengxin Zheng
Most LLM safety work studies single-agent models, but many real applications rely on multiple interacting agents. In these systems, prompt segmentation and inter-agent routing create attack surfaces that single-agent evaluations miss. We study conjunctive prompt attacks , where a trigger key in t...