LoRA Adapter Backdoor Research (arXiv:2605.30189)
Collection
Companion artifacts for "LoRA Adapter Backdoor Research" (arXiv:2605.30189): intentionally backdoored LoRA adapters and the poisoned training datasets • 34 items • Updated • 1
Travis Lelle PRO
Travis-ML
AI & ML interests
Adversarial ML and AI - LoRA Adapter Backdoors - AI-Security in general
Recent Activity
upvoted a collection 2 days ago
LoRA Adapter Backdoor Research (arXiv:2605.30189) commentedon a paper 6 days ago
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents commentedon a paper 6 days ago
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM AgentsOrganizations
upvoted a collection 2 days ago
commented 2
papers 6 days ago
updated a
model 13 days ago
published a
model 13 days ago
updated a
model 13 days ago
published a
model 13 days ago
upvoted a paper 17 days ago
published an article 19 days ago
Article
How I Backed Into AI Research by Trying to Poison My Own Model
Travis-ML
• authored a
paper 19 days ago
commented a
paper 21 days ago
updated a
collection 22 days ago