Muhammad Atif Butt

I am Ph.D. Candidate at CVC, UAB.

I am a Computer Science PhD candidate at Computer Vision Center, Universitat Autonoma De Barcelona under the supervision of Dr. Joost Van De Weijer. I am working in the Learning and Perception (LAMP) Team where my main research topic is Generative modeling, with the particular focus on personalizing generative models.

Previously, I worked as Research Assistant to Dr. Junaid Qadir at Information Technology University, where I explored Adversarial Machine Learning and Scene Understanding in Autonomous Driving.

Recent Updates!

  • [September, 2024] Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack (COPSAM) is accepted at SafeGenAI Workshop, NeurIPS 2024.
  • [August, 2024] RS100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild is accepted in International Journal of Computer Vision (IJCV).
  • [July, 2024] ColorPeel accepted at ECCV 2024, Milano! Congratulations to all co-authors.
  • [September, 2023] Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing is accepted at NeurIPS 2023.

Selected Publications

  • Privacy Protection in Personalized Diffusion Models via Targeted Cross-Attention Adversarial Attack

    Xide Xu, Muhammad Atif Butt, Sandesh Kamath, Bogdan Raducanu
    Neural Information Processing Systems (NeurIPS) 2024 Workshop, SafeGenAI
    [OpenReview] [Project (Soon)] [Code (Soon)]

  • RS100K: Road-Region Segmentation Dataset for Semi-supervised Autonomous Driving in the Wild

    Muhammad Atif Butt, Hassan Ali, Adnan Qayyum, Waqas Sultani, Ala Al-Fuqaha, Junaid Qadir
    International Journal of Computer Vision
    [PDF] [Project] [Code]

  • ColorPeel: Color Prompt Learning with Diffusion Models via Color and Shape Disentanglement

    Muhammad Atif Butt, Kai Wang, Javier Vazquez-Corral, Joost van de Weijer
    European Conference on Computer Vision (ECCV) 2024
    [PDF] [Project] [Code] [Poster]

  • Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

    Kai Wang, Fei Yang, Shiqi Yang, Muhammad Atif Butt, Joost van de Weijer
    Neural Information Processing Systems (NeurIPS) 2023
    [PDF] [Code]

  • Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models

    Hassan Ali, Muhammad Atif Butt, Fethi Filali, Ala Al-Fuqaha, Junaid Qadir
    IEEE Transactions on Intelligent Transportation Systems
    [PDF]

  • Secure and trustworthy artificial intelligence-extended reality (AI-XR) for metaverses

    Adnan Qayyum, Muhammad Atif Butt, Hassan Ali, Muhammad Usman, Osama Halabi, Ala Al-Fuqaha, Qammer H Abbasi, Muhammad Ali Imran, Junaid Qadir
    ACM Computing Surveys
    [PDF]

  • CARL-D: A vision benchmark suite and large scale dataset for vehicle detection and scene segmentation

    Muhammad Atif Butt and Faisal Riaz
    Signal Processing: Image Communication (Elsevier)
    [PDF] [Project] [Code]

  • Towards secure private and trustworthy human-centric embedded machine learning: An emotion-aware facial recognition case study

    Muhammad Atif Butt, Adnan Qayyum, Hassan Ali, Ala Al-Fuqaha, Junaid Qadir
    Computers & Security (Elsevier)
    [PDF]

  • Dental caries detection using a semi-supervised learning approach

    Adnan Qayyum, Ahsen Tahir, Muhammad Atif Butt, Alexander Luke, Hasan Tahir Abbas, Junaid Qadir, Kamran Arshad, Khaled Assaleh, Muhammad Ali Imran, Qammer H Abbasi
    Scientific Reports (Nature)
    [PDF] [Code]

  • Pixel Level Segmentation Based Drivable Road Region Detection and Steering Angle Estimation Method for Autonomous Driving on Unstructured Roads

    Marya Rasib, Muhammad Atif Butt, Faisal Riaz, Adel Sulaiman, and Muhammad Akram
    IEEE Access
    [PDF] [Project] [Code]