Yassine Yousfi

I am passionate about machine intelligence.

I work as a head of Machine Learning at comma.ai where my focus is learning driving agents from data and in an end-to-end fashion.

To do so, we’re training World Models for driving. These World Models can be seen as “simulators” generating realistic driving video given driving inputs (steering, gas, etc.). World Models are useful for many reasons:

  • They are trained with very little supervision (self-supervised training)
  • They can be used to generate synthetic data for other models to learn on-policy
  • They can be used as powerful feature extractors
  • They can be used as policies

I hold a PhD in Electrical and Computer Engineering from Binghamton University (SUNY) where I researched digital media security topics such as Steganography/Steganalysis or Watermarking Deep Learning.

The take-away from my PhD was that when carefully scaling Machine Learning architecture and data, digital media security tasks can be learned end-to-end, with little domain specific preprocessing or tricks.

I also hold a MSc in Computer Science/Machine Learning from École Centrale de Lille (France).

News

Jun 25, 2023 I’m giving a talk at comma_con titled “Learning a Driving Simulator.” Blog post coming soon.
Jun 1, 2023 I’m serving as a Technical Program Chair for the 11th ACM Workshop on Information Hiding and Multimedia Security (IH&MMSec)
Jun 28, 2022 Our new paper “Detector-Informed Batch Steganography and Pooled Steganalysis” won the Best Student Paper Award at the ACM Workshop on Information Hiding and Multimedia Security (IH&MMSEC)!
May 10, 2022 I successfully defended my Ph.D. dissertation 🎉
May 1, 2022 Excited about our new paper on Batch Steganography and Pooled Steganalysis accepted at the ACM Workshop on Information Hiding and Multimedia Security (IH&MMSEC).

Selected publications

  1. thesis
    DEEP LEARNING FOR IMAGE STEGANOGRAPHY AND STEGANALYSIS. CHALLENGES, ADVANCES, AND OPPORTUNITIES
    Yousfi, Y.
    2022
  2. IH
    Detector-Informed Batch Steganography and Pooled Steganalysis
    Yousfi, Y., Dworetzky, E., and Fridrich, J.
    In The 10th ACM Workshop on Information Hiding and Multimedia Security 2022
  3. CNN Steganalyzers Leverage Local Embedding Artifacts
    Yousfi, Y., Butora, J., and Fridrich, J.
    In IEEE International Workshop on Information Forensics and Security 2021
  4. IH
    Improving EfficientNet for JPEG Steganalysis
    Yousfi, Y., Butora, J., Fridrich, J., and Fuji-Tsang, C.
    In The 9th ACM Workshop on Information Hiding and Multimedia Security 2021
  5. ImageNet Pre-trained CNNs for JPEG Steganalysis
    Yousfi, Y., Butora, J., Khvedchenya, E., and Fridrich, J.
    In IEEE International Workshop on Information Forensics and Security 2020
  6. SPL
    An Intriguing Struggle of CNNs in JPEG Steganalysis and the OneHot Solution
    Yousfi, Y., and Fridrich, J.
    IEEE Signal Processing Letters 2020
  7. EI
    JPEG steganalysis detectors scalable with respect to compression quality
    Yousfi, Y., and Fridrich, J.
    In Proceedings IS&T, Electronic Imaging, Media Watermarking, Security, and Forensics 2020
  8. IH
    Breaking ALASKA: Color Separation for Steganalysis in JPEG Domain
    Yousfi, Y., Butora, J., Giboulot, Q., and Fridrich, J.
    In The 7th ACM Workshop on Information Hiding and Multimedia Security 2019