Suha Sabi Hussain

I'm an engineer and researcher based in Brooklyn. I work on AI/ML and systems security. Look at this page if you're curious about what I've done.

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

Disclaimer: The views expressed here are my own and do not represent those of any current or former employer or affiliated organization.

Blog Posts:

Note that ↗ denotes external work

FLAWED’s Flaws and What This Means for Industry Research — September 22, 2026
↗ How Harvey Secures Embeddings at Scale (Harvey) — April 30, 2026
↗ Weaponizing Image Scaling Against Production AI Systems (Trail of Bits) — August 21, 2025
↗ Hijacking Multi-agent Systems in Your PajaMAS (Trail of Bits) — July 31, 2025
↗ Incubated ML Exploits: Backdooring ML Pipelines Using Input-Handling Bugs (Trail of Bits & Georgia Tech) — August 20, 2024
↗ Sleepy Pickle: Hybrid ML Exploit Chaining Pickle Insecurity and Model Backdoors (Trail of Bits) — June 11, 2024
↗ Design Review of the 6079 Proof-of-Inference Protocol (Trail of Bits) — April 29, 2024
↗ Relishing New Fickling Features for Securing ML Systems (Trail of Bits) — March 4, 2024
↗ Assessing the Security Posture of a Widely Used Vision Model: YOLOv7 (Trail of Bits) — November 15, 2023
↗ Safetensors Security Assessment (Trail of Bits) — May 23, 2023
↗ Secure Your Machine Learning with Semgrep (Trail of Bits) — September 20, 2022
↗ Never a Dill Moment: Exploiting Machine Learning Pickle Files (Trail of Bits) — March 15, 2021
↗ PrivacyRaven Has Left the Nest (Trail of Bits) — October 8, 2020
The Before Times (NYU CCS & QHSS) — September 20, 2019