Model Tampering Attacks Enable More Rigorous Evaluations of LLM Capabilities
Paper
•
2502.05209
•
Published
•
1
Anirudh Satheesh
asatheesh
AI & ML interests
None yet
Recent Activity
authored
a paper
6 days ago
Model Tampering Attacks Enable More Rigorous Evaluations of LLM
Capabilities
authored
a paper
6 days ago
MORSE-500: A Programmatically Controllable Video Benchmark to
Stress-Test Multimodal Reasoning
Organizations
None yet
asatheesh's activity
authored
2
papers
6 days ago
upvoted
a
paper
8 days ago
updated
a
dataset
12 months ago
updated
a
model
12 months ago