作者位次 #4/6ICML 2026Poster· Social Aspects / Safety
Poison with Style: A Practical Poisoning Attack on Code Large Language Models
Khang Tran · Yazan Boshmaf · Issa Khalil · Hai Phan · Ting Yu · Md Rizwan Parvez
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。
Khang Tran · Yazan Boshmaf · Issa Khalil · Hai Phan · Ting Yu · Md Rizwan Parvez
Binh-Nguyen Nguyen · Khang Tran · Hai Phan · Issa Khalil
Tuan Nguyen · Naseem Khan · Khang Tran · Hai Phan · Issa Khalil
Khang Tran · Khoa Nguyen · Cristian Borcea · Hai Phan
Recent advances in large language models for test case generation have improved branch coverage via prompt-engineered mutations. However, they still lack principled mechanisms for steering models toward specific high-risk execution branches, limiting their effectiveness for discovering subtle bug...