Publications

Pre-prints, conference, journal, and workshop papers.

2022

  1. ECCV
    Generic placeholder image
    PRIME: A few primitives can boost robustness to common corruptions
    Apostolos Modas, Rahul Rade, Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In European Conference on Computer Vision 2022
    arXiv
  2. ICLR
    Generic placeholder image
    Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off
    Rahul Rade, and Seyed-Mohsen Moosavi-Dezfooli
    In International Conference on Learning Representations 2022
    PDF
  3. TRC
    Generic placeholder image
    Are socially-aware trajectory prediction models really socially-aware?
    Saeed Saadatnejad, Mohammadhossein Bahari, Pedram Khorsandi, Mohammad Saneian, Seyed-Mohsen Moosavi-Dezfooli, and Alexandre Alahi
    Transportation Research Part C: Emerging Technologies 2022
    arXiv
  4. CVPR
    Generic placeholder image
    Vehicle trajectory prediction works, but not everywhere
    Mohammadhossein Bahari, Saeed Saadatnejad, Ahmad Rahimi, Mohammad Shaverdikondori, Mohammad Shahidzadeh, Seyed-Mohsen Moosavi-Dezfooli, and Alexandre Alahi
    In IEEE Conference on Computer Vision and Pattern Recognition 2022
    arXiv

2021

  1. NeurIPS
    Generic placeholder image
    What can linearized neural networks actually say about generalization?
    Guillermo Ortiz-Jiménez, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    Advances in Neural Information Processing Systems 2021
    arXiv
  2. ICMLW Silver Best Paper Award
    Generic placeholder image
    HAT: Reducing Excessive Margin to Achieve a Better Accuracy vs. Robustness Trade-off
    Rahul Rade, and Seyed-Mohsen Moosavi-Dezfooli
    In ICML Workshop on Adversarial Machine Learning 2021
    PDF
  3. ICML
    Generic placeholder image
    Uniform Convergence, Adversarial Spheres and a Simple Remedy
    Gregor Bachmann, Seyed-Mohsen Moosavi-Dezfooli, and Thomas Hofmann
    In International Conference on Machine Learning 2021
    arXiv
  4. ICLRW
    Generic placeholder image
    A neural anisotropic view of underspecification in deep learning
    Guillermo Ortiz-Jimenez, Itamar Franco Salazar-Reque, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    RobustML Workshop 2021
    arXiv
  5. ICLRW
    Generic placeholder image
    Adversarial training may be a double-edged sword
    Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, and Huaiyu Dai
    RobustML Workshop 2021
    arXiv
  6. IEEEProc
    Generic placeholder image
    Optimism in the face of adversity: Understanding and improving deep learning through adversarial robustness
    Guillermo Ortiz-Jiménez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    Proceedings of the IEEE 2021
    arXiv

2020

  1. NeurIPS
    Generic placeholder image
    Hold me tight! Influence of discriminative features on deep network boundaries
    Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In Advances in Neural Information Processing Systems 2020
    arXiv Code Video
  2. NeurIPS
    Generic placeholder image
    Neural Anisotropy Directions
    Guillermo Ortiz-Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In Advances in Neural Information Processing Systems 2020
    arXiv Blog Code Video
  3. CVPR
    Generic placeholder image
    GeoDA: a geometric framework for black-box adversarial attacks
    Ali Rahmati, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, and Huaiyu Dai
    In IEEE Conference on Computer Vision and Pattern Recognition 2020
    arXiv Code Video
  4. ICMLW
    Generic placeholder image
    Redundant features can hurt robustness to distributions shift
    Guillermo Ortiz Jimenez, Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In Uncertainty & Robustness in Deep Learning Workshop 2020
    PDF

2019

  1. CVPR
    Generic placeholder image
    SparseFool: a few pixels make a big difference
    Apostolos Modas, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In IEEE Conference on Computer Vision and Pattern Recognition 2019
    arXiv Code
  2. CVPR
    Generic placeholder image
    Robustness via curvature regularization, and vice versa
    Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Jonathan Uesato, and Pascal Frossard
    In IEEE Conference on Computer Vision and Pattern Recognition 2019
    arXiv Code
  3. ICASSP
    Generic placeholder image
    Universal Adversarial Attacks on Text Classifiers
    Melika Behjati, Seyed-Mohsen Moosavi-Dezfooli, Mahdieh Soleymani Baghshah, and Pascal Frossard
    In International Conference on Acoustics, Speech, and Signal Processing 2019
    PDF
  4. ICCV
    Generic placeholder image
    A geometry-inspired decision-based attack
    Yujia Liu, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In International Conference on Computer Vision 2019
    arXiv

2018

  1. CVPR
    Generic placeholder image
    Empirical study of the topology and geometry of deep networks
    Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, Pascal Frossard, and Stefano Soatto
    In IEEE Conference on Computer Vision and Pattern Recognition 2018
    arXiv
  2. CVPR
    Generic placeholder image
    Geometric robustness of deep networks: analysis and improvement
    Can Kanbak, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In IEEE Conference on Computer Vision and Pattern Recognition 2018
    arXiv Code
  3. AAAI
    Generic placeholder image
    Adaptive quantization for deep neural network
    Yiren Zhou, Seyed-Mohsen Moosavi-Dezfooli, Ngai-Man Cheung, and Pascal Frossard
    In Thirty-Second AAAI Conference on Artificial Intelligence 2018
    arXiv
  4. arXiv
    Generic placeholder image
    Divide, denoise, and defend against adversarial attacks
    Seyed-Mohsen Moosavi-Dezfooli, Ashish Shrivastava, and Oncel Tuzel
    arXiv preprint arXiv:1802.06806 2018
    arXiv
  5. ICLR
    Generic placeholder image
    Robustness of classifiers to universal perturbations: A geometric perspective
    Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, Pascal Frossard, and Stefano Soatto
    In International Conference on Learning Representations 2018
    arXiv

2017

  1. CVPR
    Generic placeholder image
    Universal adversarial perturbations
    Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, Omar Fawzi, and Pascal Frossard
    In IEEE Conference on Computer Vision and Pattern Recognition 2017
    arXiv Code Video Demo
  2. SPM
    Generic placeholder image
    The robustness of deep networks: A geometrical perspective
    Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    IEEE Signal Processing Magazine 2017
    PDF

2016

  1. NeurIPS
    Generic placeholder image
    Robustness of classifiers: from adversarial to random noise
    Alhussein Fawzi, Seyed-Mohsen Moosavi-Dezfooli, and Pascal Frossard
    In Advances in Neural Information Processing Systems 2016
    arXiv
  2. CVPR
    Generic placeholder image
    DeepFool: a simple and accurate method to fool deep neural networks
    Seyed-Mohsen Moosavi-Dezfooli, Alhussein Fawzi, and Pascal Frossard
    In IEEE Conference on Computer Vision and Pattern Recognition 2016
    arXiv Code
  3. EWSN
    Generic placeholder image
    Simultaneous acoustic localization of multiple smartphones with euclidean distance matrices
    Seyed-Mohsen Moosavi-Dezfooli, Yvonne-Anne Pignolet, and Dacfey Dzung
    In International Conference on Embedded Wireless Systems and Networks 2016
    arXiv