Saeed Mahloujifar

I am a Postdoctoral Research Associate at the depertment of Electrical and Computer Engineering at Princeton University working with Prateek Mittal. I am interested in security and privacy of machine learning and their interplay with foundations of cryptography.

I received my Ph.D. from the department of Computer Science at Universit of Virginia in the summer of 2020. My Ph.D. advisor was Mohammad Mahmoody. Prior to UVa I got my B.Sc. degree in Computer Engineering from department of Computer Engineering at Sharif University of Technology in the summer of 2015. I also spent summers of 2019 and 2020 working as an Intern at Microsoft Research, Redmond.


Publications


* indicates equal contribution. [αβ] indicates alphabetical order.

Preprints

  • Property Inference from Poisoning
            [αβ] Melissa Chase, Esha Ghosh, Saeed Mahloujifar.
  • Obliviousness Makes Poisoning Adversaries Weaker
            [αβ] Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, and Abhradeep Thakurta.
            A preliminary version presented at the Uncertainty & Robustness in Deep Learning workshop at ICML 2020.
  • Conference Publications

  • Model-targeted Poisoning Attacks with Provable Convergence
            International Conference on Machine Learning (ICML) 2021.
            Fnu Suya, Saeed Mahloujifar, Anshuman Suri, David Evans, and Yuan Tian.
  • Is Private Learning Possible with Instance Encoding?
            [αβ] Nicholas Carlini, Samuel Deng, Sanjam Garg, Somesh Jha, Saeed Mahloujifar, Mohammad Mahmoody, Shuang Song, Abhradeep Thakurta, and Florian Tramér .
            IEEE Symposium on Security and Privacy (S&P) 2021.
            Also presented at the Privacy Preserving Machine Learning workshop at NeurIPS 2020.
  • Lower Bounds for Adversarially Robust PAC Learning under Evasion and Hybrid Attacks.
            Dimitrios Diochnos*, Saeed Mahloujifar*, and Mohammad Mahmoody.
            International Conference on Machine Learning and Applications (ICMLA) 2020.
  • Adversarially Robust Learning Could Leverage Computational Hardness
            [αβ] Somesh Jha, Sanjam Garg, Saeed Mahloujifar, and Mohammad Mahmoody.
            Algorithmic Learning Theory (ALT), 2020.
  • Computational Concentration of Measure: Optimal Bounds, Reductions, and More.
            [αβ] Omid Etesami, Saeed Mahloujifar, and Mohammad Mahmoody.
            ACM-SIAM Symposium on Discrete Algorithms (SODA), 2020.
  • Emprically Measuring Concentration: Fundamental Limits on Intrinsic Robustness
            Saeed Mahloujifar*, Xiao Zhang*, Mohammad Mahmoody, and David Evans.
            Conference on Neural Information Processing Systems (NeurIPS), 2019 (spotlight).
  • Universal Multi-party Poisoning Attacks
            [αβ] Saeed Mahloujifar, Mohammad Mahmoody, and Ameer Mohammed.
            International Conference on Machine Learning (ICML) 2019.
  • Can Adversarially Robust Learning Leverage Computational Hardness?
            [αβ] Saeed Mahloujifar and Mohammad Mahmoody.
            Algorithmic Learning Theory (ALT), 2019.
  • The Curse of Concentration in Robust Learning: Evasion and Poisoning Attacks from Concentration of Measure
            Saeed Mahloujifar, Dimitrios I. Diochnos, and Mohammad Mahmoody.
            AAAI Conference on Artificial Intelligence, 2019.
  • Adversarial Risk and Robustness: General Definitions and Implications for the Uniform Distribution
            Dimitrios I. Diochnos*, Saeed Mahloujifar*, and Mohammad Mahmoody.
            Conference on Neural Information Processing Systems (NeurIPS), 2018.
  • Learning under p-Tampering Attacks
            Saeed Mahloujifar, Dimitrios I. Diochnos, and Mohammad Mahmoody.
            Algorithmic Learning Theory (ALT), 2018.
            Selected to be presented at ISAIM, 2018.
  • Blockwise p-Tampering Attacks on Cryptographic Primitives, Extractors, and Learners
            [αβ] Saeed Mahloujifar and Mohammad Mahmoody.
            Theory of Cryptography Conference (TCC) 2017.
  • Near Linear-Time Community Detection in Networks with Hardly Detectable Community Structure
            Aria Rezaei, Saeed Mahloujifar, and Mahdieh Soleymani.
            Advances in Social Networks Analysis and Mining (ASONAM) 2015.
  • Journal Publications

  • Learning Under p-Tampering Poisoning Attacks
            Saeed Mahloujifar, Dimitrios Diochnos, and Mohammad Mahmoody.
            Annals of Mathematics and Artificial Intelligence, Vol. 88, pp. 759--792, 2020.

  • Contact


    Mailing Address:

    Saeed Mahlouji Far
    Department of Electrical and Computer Engineering
    Princeton University
    Princeton, NJ, 08544

    Email: