Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration
Paper • 2609.16204 • Published • 4
Aashiq Muhamed
aashiqmuhamed
AI & ML interests
None yet
Recent Activity
authored a paper 4 days ago
Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration authored a paper 4 days ago
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks authored a paper 4 days ago
MOLE: Detecting Insider Threats in AI AgentsOrganizations
authored 5
papers 4 days ago
Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Paper • 2609.15029 • Published • 8
MOLE: Detecting Insider Threats in AI Agents
Paper • 2609.06966 • Published • 18
Beyond Understanding: Evaluating the Pragmatic Gap in LLMs' Cultural Processing of Figurative Language
Paper • 2510.23828 • Published • 2
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
Paper • 2510.10390 • Published • 5
upvoted a paper 5 days ago
submitted a
paper to Daily Papers 5 days ago
upvoted a paper 6 days ago
submitted a
paper to Daily Papers 6 days ago
updated a
dataset 12 days ago
upvoted a paper 12 days ago
submitted a
paper to Daily Papers 12 days ago
liked a
dataset 14 days ago
published a
dataset 14 days ago
updated a
dataset about 1 month ago
published a
dataset about 1 month ago
published 4
models 2 months ago