Publications

⠀* indicates equal contribution.

2026

  1. Preprint
    MobileWan: Closing the Quality Gap for Mobile Video Diffusion
    Mohsen Ghafoorian*, Denis Korzhenkov*Adil Karjauv*, Ioannis Lelekas*, and 7 more authors
    Preprint, 2026
  2. CVPR 2026
    PyramidalWan: On Making Pretrained Video Model Pyramidal for Efficient Inference
    Denis Korzhenkov*Adil Karjauv*, Animesh Karnewar, Mohsen Ghafoorian, and 1 more author
    Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
  3. ICLR 2026
    Neodragon: Mobile Video Generation Using Diffusion Transformer
    Animesh Karnewar, Denis Korzhenkov, Ioannis Lelekas, Adil Karjauv, and 7 more authors
    Proceedings of the International Conference on Learning Representations (ICLR), 2026

2025

  1. CVPR 2025 Workshop
    AdapToR: Adaptive Token Reduction for Video Diffusion Transformers
    Elia Peruzzo, Adil Karjauv, Nicu Sebe, Amir Ghodrati, and 1 more author
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2025

2024

  1. Preprint
    MoViE: Mobile Diffusion for Video Editing
    Adil Karjauv*, Noor Fathima*, Ioannis Lelekas, Fatih Porikli, and 2 more authors
    Preprint, 2024
  2. ECCV 2024
    Object-Centric Diffusion for Efficient Video Editing
    Kumara Kahatapitiya, Adil Karjauv, Davide Abati, Fatih Porikli, and 2 more authors
    In European Conference on Computer Vision (ECCV), 2024

2023

  1. ACM MM 2023
    Simple Techniques are Sufficient for Boosting Adversarial Transferability
    Chaoning Zhang, Philipp Benz, Adil Karjauv, In So Kweon, and 1 more author
    In Proceedings of the 31st ACM International Conference on Multimedia (ACM MM), 2023

2022

  1. CVPR 2022
    Investigating Top-k White-Box and Transferable Black-box Attack
    Chaoning Zhang, Philipp Benz, Adil Karjauv, Jae Won Cho, and 2 more authors
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022

2021

  1. BMVC 2021
    Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNs
    Philipp Benz*, Soomin Ham*, Chaoning Zhang*Adil Karjauv, and 1 more author
    In British Machine Vision Conference (BMVC), 2021
  2. ACM MM 2021
    Towards Robust Deep Hiding Under Non-Differentiable Distortions for Practical Blind Watermarking
    Chaoning Zhang*Adil Karjauv*, Philipp Benz*, and In So Kweon
    In Proceedings of the 29th ACM International Conference on Multimedia (ACM MM), 2021
  3. ICCV 2021
    Data-free Universal Adversarial Perturbation and Black-box Attack
    Chaoning Zhang*, Philipp Benz*Adil Karjauv*, and In So Kweon
    In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021
  4. IJCAI 2021
    A Survey on Universal Adversarial Attack
    Chaoning Zhang*, Philipp Benz*, Chenguo Lin*Adil Karjauv, and 2 more authors
    In International Joint Conference on Artificial Intelligence (IJCAI), 2021
  5. ICME 2021
    Universal Adversarial Training with Class-Wise Perturbations
    Philipp Benz*, Chaoning Zhang*Adil Karjauv, and In So Kweon
    In 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021
  6. ICME 2021
    Motionsnap: A Motion Sensor-Based Approach for Automatic Capture and Editing of Photos and Videos on Smartphones
    Adil Karjauv*, Sanzhar Bakhtiyarov*, Chaoning Zhang, Jean-Charles Bazin, and 1 more author
    In 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021
  7. AAAI 2021
    Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective
    Chaoning Zhang*, Philipp Benz*Adil Karjauv, and In So Kweon
    In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021
  8. WACV 2021
    Revisiting Batch Normalization for Improving Corruption Robustness
    Philipp Benz*, Chaoning Zhang*Adil Karjauv, and In So Kweon
    In Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2021
  9. CVPR Workshop 2021
    Is FGSM Optimal or Necessary for L∞ Adversarial Attack?
    Chaoning Zhang*Adil Karjauv*, Philipp Benz*, Soomin Ham, and 3 more authors
    In Workshop on Adversarial Machine Learning in Real-World Computer Vision Systems and Online Challenges (CVPR AML-CV Workshop), 2021
  10. ICLR Workshop 2021
    On Strength and Transferability of Adversarial Examples: Stronger Attack Transfers Better
    Chaoning Zhang*, Philipp Benz*Adil Karjauv*, and In So Kweon
    In Robust and Reliable Machine Learning in the Real World Workshop (ICLR Workshop), 2021
  11. ICLR Workshop 2021
    Stochastic Depth Boosts Transferability of Non-targeted and Targeted Adversarial Attacks
    Chaoning Zhang*, Philipp Benz*Adil Karjauv*, and In So Kweon
    In Robust and Reliable Machine Learning in the Real World Workshop (ICLR Workshop), 2021
  12. ICLR Workshop 2021
    Towards Data-free Universal Adversarial Perturbations with Artificial Jigsaw Images
    Chaoning Zhang*, Philipp Benz*Adil Karjauv*, Jae Won Cho, and 1 more author
    In Robust and Reliable Machine Learning in the Real World Workshop (ICLR Workshop), 2021

2020

  1. NeurIPS 2020
    UDH: Universal Deep Hiding for Steganography, Watermarking, and Light Field Messaging
    Chaoning Zhang*, Philipp Benz*Adil Karjauv*, Geng Sun, and 1 more author
    Advances in Neural Information Processing Systems (NeurIPS), 2020