CS grad researcher @ Texas Tech — ML security, Network Security & Adversarial ML, tool-use evaluation, interpretability
-
Texas Tech University
- Lubbock, TX
- https://whoismdarahman.com
Pinned Loading
-
saeguardbench
saeguardbench PublicDo SAE Features Actually Help Detect Jailbreaks? A Systematic Benchmark of Interpretability-Based Safety Methods
Python
-
comptoolbench
comptoolbench PublicCompToolBench: Measuring Compositional Tool-Use Generalization in LLMs — 200 tasks, 106 tools, 18 models, 4 composition levels
Python
-
traffic-fingerprinting
traffic-fingerprinting PublicTraffic Fingerprinting with Machine Learning
Python
-
LiDAR-Infrastructure-Safety-TxDOT
LiDAR-Infrastructure-Safety-TxDOT PublicReal-time LiDAR data processing system for infrastructure safety analytics, developed for the Texas Department of Transportation (TxDOT). Includes packet decoding, point cloud conversion, and times…
Python
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.
