Hamid Mozaffari

I am an AI research scientist at Oracle, where I develop methods for auditing the security, privacy, and alignment of large language models and agentic systems. My research includes automated red teaming, reinforcement-learning-based evaluation, memorization and membership-inference auditing, access-control evaluation, and content-moderation robustness. I am particularly interested in building rigorous and scalable evaluation frameworks that uncover hidden failures in deployed AI systems.

I earned my Ph.D. in Computer Science from University of Massachusetts Amherst, where I was advised by Professor Amir Houmansadr. My doctoral research focused on the security, privacy, fairness, and robustness of federated learning.

News #

Research interests #

Selected publications #

  1. 2026

    Auditing Moderation Robustness Under Realistic Settings

    Bargav Jayaraman*, Hamid Mozaffari*, Virendra Marathe, Sarthak Panda

    Conference on Language Modeling (COLM), 2026 · *Equal contribution

  2. 2025

    Permissioned LLMs: Enforcing Access Control in Large Language Models

    Bargav Jayaraman, Virendra Marathe, Hamid Mozaffari, W. Shen, Krishnaram Kenthapadi

    Neural Information Processing Systems (NeurIPS), 2025

  3. 2024

    Semantic Membership Inference Attack against Large Language Models

    Hamid Mozaffari, Virendra Marathe

    RedTeaming GenAI Workshop, NeurIPS 2024

  4. 2024

    Fake or Compromised? Making Sense of Malicious Clients in Federated Learning

    Hamid Mozaffari, Sunav Choudhary, Amir Houmansadr

    European Symposium on Research in Computer Security (ESORICS), 2024

  5. 2023

    Every Vote Counts: Ranking-Based Training of Federated Learning to Resist Poisoning Attacks

    Hamid Mozaffari, Virat Shejwalkar, Amir Houmansadr

    32nd USENIX Security Symposium, 2023

  6. 2022

    FedPerm: Private and Robust Federated Learning by Parameter Permutation

    Hamid Mozaffari, Virendra J. Marathe, Dave Dice

    FL Workshop, NeurIPS 2022

  7. 2022

    Equity and Equality in Fair Federated Learning

    Hamid Mozaffari, Amir Houmansadr

    ICML 2022 Workshop on Responsible Decision Making in Dynamic Environments (RDMDE)

  8. 2022

    Robust Federated Learning by Training on Parameter Ranks

    Hamid Mozaffari, Virat Shejwalkar, Amir Houmansadr

    FL-AAAI 2022

  9. 2020

    Heterogeneous Private Information Retrieval

    Hamid Mozaffari, Amir Houmansadr

    Network and Distributed System Security Symposium (NDSS), 2020

For the full list, please refer to my Google Scholar page.