About Me

Hi! My name is Suha Sabi Hussain. I'm an AI/ML security engineer.

You can contact me at suhashussain1 ‘at’ gmail ‘dot’ com or @suhackerr on Twitter.

Select Works

Trail of Bits

Weaponizing Image Scaling Against Production AI Systems
Hijacking Multi-agent Systems in Your PajaMAS

Incubated Machine Learning Exploits: Backdooring ML Pipelines Using Input-Handling Bugs

Lightweight Design Review of the 6079 Proof-of-Inference Protocol (Public Report)

Meta WhatsApp Private Processing Security Assessment (Public Report)

EZKL Security Assessment (Public Report)

Sleepy Pickle: Hybrid ML Exploit Chaining Pickle Insecurity and Model Backdoors

Relishing New Fickling Features for Securing ML Systems 

ML File Formats Collection (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 

Safetensors Security Assessment (Public Report)
Secure Your Machine Learning with Semgrep 
DEF CON 30 AI Village: Panel: The Use of AI/ML in Offensive Security Operations. 
ToB Podcast Episode: W/Internships
Never a Dill Moment: Exploiting Machine Learning Pickle Files 
PrivacyRaven: Comprehensive Privacy Testing for Deep Learning 

NYU CCS

COPPTCHA: COPPA Tracking by Checking Hardware-Level Activity 
A New Method for the Exploitation of Speech Recognition Systems