Publications

Research on trustworthy machine learning, fairness, and the security of AI systems.

arXiv preprint · 2026

Surviving the Router: Optimizing Skill Injections for Retrieval and Execution

Haneen Najjar, Luca Scionis, Haritz Puerto, Sahar Abdelnabi

AI Safety
LLM Security
Prompt Injection

Paper Poster PDF Code

USENIX Security 2026

Sy-FAR: Symmetry-based Fair Adversarial Robustness

Haneen Najjar, Eyal Ronen, Mahmood Sharif

Trustworthy AI
Adversarial Robustness
Fairness

Paper Poster PDF arXiv Code