Travis Lelle
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2AI×2NLP×2ML×2
Research Timeline
2026
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
This paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing that the resulting backdoor generalizes at the token feature level, and proposes robust behavioral and weight-level detection methods.
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
The paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing the backdoor generalizes at the token feature level, and proposes robust behavioral and weight-level detectors for detection.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIcs.CLRecentMay 28, 2026
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection
This paper demonstrates that LoRA adapters can be backdoored via data poisoning, showing that the resulting backdoor generalizes at the token feature level, and proposes robust behavioral and weight-l…
View →
cs.CRcs.AIcs.CLRecentMay 28, 2026