Chris Russell

It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

Face-Feature Tuning: Post-hoc Calibration for Fair and Accurate Deepfake Detection

Fairness by Design: Efficient Fair Ensembles for Low-Data Classification

To Distill or Not to Distill: Knowledge Transfer Undermines Safety of LLMs

Adaptive Calibration for Fairer Facial Recognition

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

Watermarking for User Identification in Large Language Models