49 citations · 93 across the 15 of their papers we have counts for
Showing cs.CRShow all
2 papers · 1 filter
cs.CR2026
OPBackdoor: Opportunistic Backdoors via Alibi-Aligned Reasoning
Eric Xue, Ruiyi Zhang, Kevin Xue +3
When a backdoor trigger activates the target response regardless of the triggered prompt context, the backdoor objective reveals itself. Challenging this trigger-sufficient formula…
cs.CR2025
SteganoBackdoor: Evading Data-Poisoning Defenses via Steganographic Backdoors
Eric Xue, Ruiyi Zhang, Pengtao Xie
Transformer-based models are highly susceptible to backdoor attacks via supervised fine-tuning (SFT). To red-team existing data-poisoning defenses, prior work has increasingly focu…