MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning.
Yizhe Zeng, Wei Zhang, Yunpeng Li, Juxin Xiao, Xiao Wang, Yuling Liu
Browse the full ACL paper archive.
Yizhe Zeng, Wei Zhang, Yunpeng Li, Juxin Xiao, Xiao Wang, Yuling Liu
Browse the full ACL paper archive.