Amir Houmansadr

Bias Similarity Measurement: A Black-Box Audit of Fairness Across LLMs

Forget to Know, Remember to Use: Context-Aware Unlearning for Large Language Models

Bob’s Confetti: Phonetic Memorization Attacks in Music and Video Generation

Can Large Language Models Really Recognize Your Name?

Multilingual and Multi-Accent Jailbreaking of Audio LLMs

Backdooring Bias into Text-to-Image Models

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification