Forge Lab

university

https://www.cs.cmu.edu/~smithv/

AI & ML interests

None defined yet.

Recent Activity

aashiqmuhamed authored a paper 7 days ago

Decoy Direction Optimization: A Post-Hoc Defense Against LLM Abliteration

aashiqmuhamed authored a paper 7 days ago

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

aashiqmuhamed authored a paper 7 days ago

MOLE: Detecting Insider Threats in AI Agents

View all activity

models 0

None public yet

datasets 5

forgelab/mole

Viewer • Updated 15 days ago • 24.9M • 230 • 1

forgelab/ParallelPrompt

Viewer • Updated Sep 22, 2025 • 37.1k • 24 • 1

forgelab/BLUR

Viewer • Updated May 16, 2025 • 10.1k • 401

forgelab/wmdp-swap

Viewer • Updated Mar 16, 2025 • 14.2k • 34 • 1

forgelab/tofu-pair

Viewer • Updated Mar 4, 2025 • 396 • 10