Kassem Fawaz

The paper introduces Narriva, a method that generates text-based synthetic privacy personas grounded in past user behavior to accurately and efficiently simulate individual and population-level privacy decisions for LLMs.

The paper introduces WebSP-Eval, a new framework to evaluate web agents on complex website security and privacy tasks, finding that current state-of-the-art models struggle significantly with stateful UI elements like toggles and checkboxes.

This paper analyzes the performance of agentic LLM systems in complex binary reverse engineering, identifying key limitations such as handling obfuscation and token constraints, and proposing future design directions.

The paper introduces Sparse Backdoor, a novel supply-chain attack that embeds a provably undetectable backdoor into pre-trained image classifiers by injecting structured sparse perturbations.

The paper characterizes the optimal achievable rate for differentially private hypothesis testing using e-values, providing an exact algorithm for both fixed and sequential settings.