Article
Travis Lelle PRO
Travis-ML
AI & ML interests
Adversarial ML and AI - LoRA Adapter Backdoors - AI-Security in general
Recent Activity
published an article about 3 hours ago
How I Backed Into AI Research by Trying to Poison My Own Model authored a paper about 12 hours ago
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection commentedon a paper 2 days ago
Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral Detection