Publications

Google Scholar (*equal contribution, †corresponding author)

  1. 2024
    • Stop Reasoning! When Multimodal LLMs with Chain-of-Thought Reasoning Meets Adversarial Images [PDF]
      Zefeng Wang, Zhen Han, Shuo Chen, Fan Xue, Zifeng Ding, Xun Xiao, Volker Tresp, Philip Torr, Jindong Gu
      Conference On Language Modeling (COLM) , 2024
    • As Firm As Their Foundations: Creating Transferable Adversarial Examples Across Downstream Tasks with CLIP [PDF]
      Anjun Hu, Jindong Gu, Francesco Pinto, Konstantinos Kamnitsas, Philip Torr
      The British Machine Vision Conference (BMVC) , 2024
    • Model-agnostic Origin Attribution of Generated Images with Few-shot Examples [PDF]
      Fengyuan Liu, Haochen Luo, Yiming Li, Philip Torr, Jindong Gu
      European Conference on Computer Vision (ECCV) , 2024
    • Improving Adversarial Transferability via Model Alignment [PDF]
      Avery Ma, Amir-massoud Farahmand, Yangchen Pan, Philip Torr, Jindong Gu
      European Conference on Computer Vision (ECCV) , 2024
    • Latent Guard: a Safety Framework for Text-to-image Generation [PDF]
      Runtao Liu, Ashkan Khakzar, Jindong Gu, Qifeng Chen, Philip Torr, Fabio Pizzati
      European Conference on Computer Vision (ECCV) , 2024
    • MM-SafetyBench: A Benchmark for Safety Evaluation of Multimodal Large Language Models [PDF]
      Xin Liu, Yichen Zhu, Jindong Gu, Yunshi Lan, Chao Yang, Yu Qiao
      European Conference on Computer Vision (ECCV) , 2024
    • Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model [PDF]
      Hao Cheng, Erjia Xiao, Jindong Gu, Le Yang, Jinhao Duan, Jose Zhang, Jiahang Cao, Kaidi Xu, Renjing Xu
      European Conference on Computer Vision (ECCV) , 2024
    • Dataset Distillation by Automatic Training Trajectories
      Dai Liu, Jindong Gu, Hu Cao, Carsten Trinitis, Martin Schulz
      European Conference on Computer Vision (ECCV) , 2024
    • Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averaging [PDF]
      Xiaojun Jia, Yuefeng Chen, Xiaofeng Mao, Ranjie Duan, Jindong Gu, Rong Zhang, Hui Xue, Xiaochun Cao
      IEEE Transactions on Information Forensics & Security (TIFS) , 2024
    • Provably Better Explanations with Optimized Aggregation of Feature Attributions
      Thomas Decker, Ananta R. Bhattarai, Jindong Gu, Volker Tresp, Florian Buettner
      International Conference on Machine Learning (ICML) , 2024
    • A Survey on Transferability of Adversarial Examples across Deep Neural Networks [PDF][CODE]
      Jindong Gu, Xiaojun Jia, Pau de Jorge, Wenqain Yu, Xinwei Liu, Avery Ma, Yuan Xun, Anjun Hu, Ashkan Khakzar, Zhijiang Li, Xiaochun Cao, Philip Torr
      Transactions on Machine Learning Research (TMLR) , 2024
    • Boosting Fair Classifier Generalization through Adaptive Priority Reweighing[PDF][CODE]
      Zhihao Hu, Yiran Xu, Mengnan Du, Jindong Gu, Xinmei Tian, Fengxiang He
      ACM Transactions on Knowledge Discovery from Data (TKDD) , 2024
    • Self-Discovering Interpretable Diffusion Latent Directions for Responsible Text-to-Image Generation [PDF][CODE]
      Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, Jindong Gu
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
    • Initialization Matters for Adversarial Transfer Learning [PDF][CODE]
      Andong Hua, Jindong Gu, Zhiyu Xue, Nicholas Carlini, Eric Wong, Yao Qin
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
    • Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds [PDF][CODE]
      Tianrui Lou, Xiaojun Jia, Jindong Gu, Li Liu, Siyuan Liang, Bangyan He, Xiaochun Cao
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2024
    • An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models [PDF][CODE]
      Haochen Luo*, Jindong Gu*, Fengyuan Liu, Philip Torr
      International Conference on Learning Representations (ICLR) , 2024
    • Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images [PDF][CODE]
      Kuofeng Gao, Yang Bai, Jindong Gu, Shu-Tao Xia, Philip Torr, Zhifeng Li, Wei Liu
      International Conference on Learning Representations (ICLR) , 2024
    • Influencer Backdoor Attack on Semantic Segmentation [PDF][CODE]
      Haoheng Lan*, Jindong Gu*, Philip Torr, Hengshuang Zhao
      International Conference on Learning Representations (ICLR) , 2024
    • Minimalism is King! High-Frequency Energy-based Screening for Data-Efficient Backdoor Attacks [PDF]
      Yuan Xun, Xiaojun Jia, Jindong Gu, Xinwei Liu, Qing Guo, Xiaochun Cao
      IEEE Transactions on Information Forensics & Security (TIFS) , 2024
    • Does Few-shot Learning Suffer from Backdoor Attacks? [PDF]
      Xinwei Liu, Xiaojun Jia, Jindong Gu, Yuan Xun, Siyuan Liang, Xiaochun Cao
      Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2024
    • FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning [PDF]
      Haokun Chen, Yao Zhang, Denis Krompass, Jindong Gu†, Volker Tresp
      Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2024
    • Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression [PDF]
      Xuanlong Yu, Gianni Franchi, Jindong Gu, Emanuel Aldea
      Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) , 2024
    • Fast Propagation is Better: Accelerating Single-Step Adversarial Training via Sampling Subnetworks [PDF]
      Xiaojun Jia, Jianshu Li, Jindong Gu†, Yang Bai, Xiaochun Cao
      IEEE Transactions on Information Forensics & Security (TIFS) , 2024
    2023
    • Benchmarking Robustness of Adaptation Methods on Pre-trained VLMs [PDF][CODE]
      Shuo Chen*, Jindong Gu*, Zhen Han, Yunpu Ma, Philip Torr, Volker Tresp
      Dataset and Benchmark Track in (NeurIPS), 2023
    • Do DALL-E and Flamingo Understand Each Other? [PDF][CODE]
      Hang Li*, Jindong Gu*, Rajat Koner, Sahand Sharifzadeh, Volker Tresp
      International Conference on Computer Vision (ICCV), 2023
    • Multi-event Video-Text Retrieval [PDF][CODE]
      Gengyuan Zhang, Jisen Ren, Jindong Gu†, Volker Tresp
      International Conference on Computer Vision (ICCV), 2023
    • FRAug: Tackling Federated Learning with Non-IID Features via Representation Augmentation [PDF]
      Haokun Chen, Ahmed Frikha, Denis Krompass, Jindong Gu†, Volker Tresp
      International Conference on Computer Vision (ICCV), 2023
    • Exploring Non-additive Randomness on ViT against Query-Based Black-Box Attacks [PDF]
      Jindong Gu, Fangyun Wei, Philip Torr, Han Hu
      British Machine Vision Conference (BMVC), 2023
    • Backdoor Defense via Adaptively Splitting Poisoned Dataset [PDF][CODE]
      Kuofeng Gao*, Yang Bai*, Jindong Gu†, Yong Yang, Shu-Tao Xia†
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2023
    • ECOLA: Enhancing Temporal Knowledge Embeddings with Contextualized Language Representations [PDF][CODE]
      Zhen Han, Ruotong Liao, Jindong Gu, Yao Zhang, Zifeng Ding, Yujia Gu, Heinz Koeppl, Hinrich Schütze, Volker Tresp
      Findings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2023
    2022
    • Are Vision Transformers robust to Patch-wise Perturbation? [PDF][CODE]
      Jindong Gu, Volker Tresp, Yao Qin
      European Conference on Computer Vision (ECCV) , 2022
    • SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustness [PDF]
      Jindong Gu, Hengshuang Zhao, Volker Tresp, Phillip Torr
      European Conference on Computer Vision (ECCV) , 2022
    • Towards Efficient Adversarial Training on Vision Transformers [PDF]
      Boxi Wu*, Jindong Gu*, Zhifeng Li, Deng Cai, Xiaofei He, Wei Liu
      European Conference on Computer Vision (ECCV) , 2022
    • Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removal [PDF][CODE]
      Liu Xinwei, Jian Liu, Yang Bai, Jindong Gu, Tao Chen, Xiaojun Jia, Xiaochun Cao
      European Conference on Computer Vision (ECCV) , 2022
    2021
    • Simple Distillation Baselines for Improving Small Self-supervised Models [PDF] [CODE]
      Jindong Gu, Wei Liu, Yonglong Tian
      Workshop in ICCV , 2021
    • Capsule Network is Not More Robust than Convolutional Network [PDF][cn Blog]
      Jindong Gu, Volker Tresp, Han Hu
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2021
    • Effective and Efficient Vote Attack on Capsule Networks [PDF][CODE]
      Jindong Gu, Baoyuan Wu, Volker Tresp
      International Conference on Learning Representations (ICLR) , 2021
    • Interpretable Graph Capsule Networks for Object Recognition [PDF] [CODE]
      Jindong Gu
      AAAI Conference on Artificial Intelligence (AAAI) , 2021
    2020
    • Improving the Robustness of Capsule Networks to Image Affine Transformations [PDF][CODE]
      Jindong Gu, Volker Tresp
      IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2020
    • Search for Better Students to Learn Distilled Knowledge [PDF][Blog]
      Jindong Gu, Volker Tresp
      European Conference on Artificial Intelligence (ECAI) , 2020
    2019
    • Neural network memorization dissection [PDF]
      Jindong Gu, Volker Tresp
      Workshop on Machine Learning with Guarantees, NeurIPS , 2019
    • Saliency Methods for Explaining Adversarial Attacks [PDF]
      Jindong Gu, Volker Tresp
      Human-Centric Machine Learning Workshop, NeurIPS , 2019
    2018
    • Understanding Individual Decisions of CNNs via Contrastive Backpropagation [PDF] [CODE]
      Jindong Gu, Yinchong Yang, Volker Tresp
      Asian Conference on Computer Vision (ACCV), 2018

Patents and Inventions

    • Verification of classification decisions in Convolutional Neural Networks [PDF]
      Jindong Gu
      US Patent: US 2022/0019870 A1
    • Method and processing unit for computer-implemented analysis of a classification model [PDF]
      Jindong Gu
      US Patent: US 2020/0334489 A1
    • Siemens Inventions: 8 AI Inventions in Siemens Technology, Germany [Link]