Portait

Amir Sadovnik

Research Lead, Center for AI Security Research (CAISER)

Contact

SADOVNIKA@ORNL.GOV

All Publications

On the Abuse and Detection of Polyglot Files

The Effects of Compounded Model Size Reductions on Adversarial Robustness

Lantern: An Interactive Adversarial AI Workbench

Assessing Membership Inference Attacks under Distribution Shifts

Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targeted Object Removal from Images

Semantic Stealth: Crafting Covert Adversarial Patches for Sentiment Classifiers Using Large Language Models

Towards a High Fidelity Training Environment for Autonomous Cyber Defense Agents

Key Links

ORCID

LinkedIn