3 papers
cs.CL2026
Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution
Yijun Liao, Fanwei Liang
When a context asserts two values for one fact, a model commits to a cue -- recency, repetition, position -- but natural data rarely makes these disagree, so behavior cannot reveal…
cs.CR2025
FFCBA: Feature-based Full-target Clean-label Backdoor Attacks
Yangxu Yin, Honglong Chen, Yudong Gao +4
Backdoor attacks pose a significant threat to deep neural networks, as backdoored models would misclassify poisoned samples with specific triggers into target classes while maintai…
cs.CR2025
SFIBA: Spatial-based Full-target Invisible Backdoor Attacks
Yangxu Yin, Honglong Chen, Yudong Gao +3
Multi-target backdoor attacks pose significant security threats to deep neural networks, as they can preset multiple target classes through a single backdoor injection. This allows…