Hi! My name is Suha Sabi Hussain.
I’m a security engineer on the AI/ML assurance team at Trail of Bits. I’ve worked on projects such as the Safetensors security audit and Fickling. I received my BS in Computer Science from Georgia Tech (with threads in people and theory).
Outside of work, I'm a member of Hack Manhattan, a practitioner of Brazilian Jiu-Jitsu, and an appreciator of NYC restaurants.
You can contact me at suhashussain1 ‘at’ gmail ‘dot’ com or @suhackerr on Twitter.
Incubated Machine Learning Exploits: Backdooring ML Pipelines Using Input-Handling Bugs
Sleepy Pickle: Hybrid ML Exploit Chaining Pickle Insecurity and Model Backdoors
List of ML File Formats (GitHub Repository)
MLFiles - Using Input-Handling Bugs to Inject Backdoors Into Machine Learning Pipelines
Assessing the security posture of a widely used vision model: YOLOv7