Publications

Preprints

* indicates Equal Contribution

• Interpreting Adversarial Examples by Activation Promotion and Suppression
  • Kaidi Xu, Sijia Liu, Gaoyuan Zhang, Mengshu Sun, Pu Zhao, Quanfu Fan, Chuang Gan, Xue Lin
• Zeroth-Order Hybrid Gradient Descent: Towards A Principled Black-Box Optimization Framework
  • Pranay Sharma, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Xue Lin, Pramod K. Varshney.

Conference Publications

* indicates Equal Contribution

• [22’ICML] A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks
  • Huan Zhang, Shiqi Wang, Kaidi Xu, Yihan Wang, Suman Jana, Cho-Jui Hsieh, Zico Kolter
  • International Conference on Machine Learning (ICML 2022)
• [21’NeurIPS] Beta-CROWN: Efficient Bound Propagation withPer-neuron Split Constraints for Neural NetworkRobustness Verification
  • Shiqi Wang*, Huan Zhang*, Kaidi Xu*, Xue Lin, Suman Jana, Cho-Jui Hsieh, J Zico Kolter
  • Neural Information Processing Systems (NeurIPS 2021)
• [21’NeurIPS] ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers
  • Husheng Han*, Kaidi Xu*, Xing Hu, Xiaobing Chen, Ling Liang, Zidong Du, Qi Guo, Yanzhi Wang, Yunji Chen
  • Neural Information Processing Systems (NeurIPS 2021)
• [21’ICLR] On Fast Adversarial Robustness Adaptation in Model-Agnostic Meta-Learning
  • Ren Wang, Kaidi Xu, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Chuang Gan, Meng Wang
  • International Conference on Learning Representations (ICLR 2021)
• [21’ICLR] Fast and Complete: Enabling Complete Neural Network Verification with Rapid and Massively Parallel Incomplete Verifiers
  • Kaidi Xu*, Huan Zhang*, Shiqi Wang, Yihan Wang, Suman Jana, Xue Lin, Cho-Jui Hsieh
  • International Conference on Learning Representations (ICLR 2021)
• [20’NeurIPS] Automatic Perturbation Analysis for Scalable Certified Robustness and Beyond
  • Kaidi Xu*, Zhouxing Shi*, Huan Zhang*, Yihan Wang, Kai-Wei Chang, Minlie Huang, Bhavya Kailkhura, Xue Lin, Cho-Jui Hsieh
  • Neural Information Processing Systems (NeurIPS 2020)
• [20’ECCV Spotlight] Adversarial T-shirt!Evading Person Detectors in A Physical World
  • Kaidi Xu, Gaoyuan Zhang, Sijia Liu, Quanfu Fan, Mengshu Sun, Hongge Chen, Pin-Yu Chen, Yanzhi Wang, Xue Lin
  • European Conference on Computer Vision (ECCV 2020)
• [20’ICML] Min-Max Optimization without Gradients: Convergence and Applications to Black-Box Evasion and Poisoning Attacks
  • Sijia Liu*, Songtao Lu*, Xiangyi Chen*, Yao Feng*, Kaidi Xu*, Abdullah Al-Dujaili, Minyi Hong, Una-May O’Reilly
  • International Conference on Machine Learning (ICML 2020)
• [20’CVPR] Light-weight Calibrator: a Separable Component for Unsupervised Domain Adaptation
  • Shaokai Ye, Kailu Wu, Mu Zhou, Yunfei Yang, Kaidi Xu, Jiebo Song, Aojun Zhou, Chenglong Bao, Kaisheng Ma,
  • Computer Vision and Pattern Recognition. (CVPR 2020)
• [20’ICASSP] Towards an Efficient and General Framework of Robust Training for Graph Neural Networks
  • Kaidi Xu, Sijia Liu, Pin-Yu Chen, Mengshu Sun, Caiwen Ding, Bhavya Kailkhura, Xue Lin
  • International Conference on Acoustics, Speech, and Signal Processing. (ICASSP 2020)
• [19’NeurIPS] ZO-AdaMM: Zeroth-Order Adaptive Momentum Method for Black-Box Optimization
  • Xiangyi Chen*, Sijia Liu*, Kaidi Xu*, Xingguo Li, Xue Lin, Mingyi Hong, David Cox
  • Neural Information Processing Systems (NeurIPS 2019)
• [19’ICCV] Adversarial Robustness vs Model Compression, or Both?
  • Kaidi Xu*, Shaokai Ye*, Sijia Liu, Jan-Henrik Lambrechts, Huan Zhang, Kaisheng Ma, Yanzhi Wang, Xue Lin
  • International Conference on Computer Vision. (ICCV 2019)
• [19’ICCV] On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method
  • Pu Zhao, Sijia Liu, Pin-Yu Chen, Nghia Hoang, Kaidi Xu, Bhavya Kailkhura, Xue Lin,
  • International Conference on Computer Vision (ICCV 2019)
• [19’IJCAI] Topology Attack and Defense for Graph Neural Networks: An Optimization Perspective
  • Kaidi Xu, Hongge Chen, Sijia Liu, Pin-Yu Chen, Tsui-Wei Weng, Mingyi Hong, Xue Lin
  • International Joint Conferences on Articial Intelligence (IJCAI 2019)
• [19’FPGA] REQ-YOLO: A Resource- Aware, Efficient Quantization Framework for Object Detection on FPGAs
  • Caiwen Ding, Shuo Wang, Ning Liu, Kaidi Xu, Yanzhi Wang, Yun Liang
  • International Symposium on Field-Programmable Gate Arrays (FPGA 2019)
• [19’ASP-DAC] ADMM Attack: An Enhanced Adversarial Attack for Deep Neural Networks with Undetectable Distortions
  • Pu Zhao, Kaidi Xu, Sijia Liu, Yanzhi Wang, Xue Lin
  • Asia and South Pacific Design Automation Conference (ASP-DAC 2019)
• [19’ICLR] Structured Adversarial Attack: Towards General Implementation and Better Interpretability
  • Kaidi Xu, Sijia Liu, Pu Zhao, Pin-Yu Chen, Huan Zhang, Deniz Erdogmus, Yanzhi Wang, Xue Lin
  • International Conference on Learning Representations (ICLR 2019)
• [18’GlobalSIP] Reinforced Adversarial Attacks on Deep Neural Networks Using ADMM
  • Pu Zhao, Kaidi Xu, Tianyun Zhang, Makan Fardad, Yanzhi Wang, Xue Lin
  • IEEE Global Conference on Signal and Information Processing (GlobalSIP 2018)
• [17’AAAI] Asymmetric Discrete Graph Hashing
  • Xiaoshuang Shi, Fuyong Xing, Kaidi Xu, Manish Sapkota, Lin Yang
  • Association for the Advancement of Artificial Intelligence (AAAI 2017)

Journal Publications

• [TIP] Loss-based Attention for Interpreting Image-level Prediction of Convolutional Neural Networks
  • Xiaoshuang Shi, Fuyong Xing, Kaidi Xu, Pingjun Chen, Yun Liang, Zhiyong Lu, Zhenhua Guo
  • IEEE Transactions on Image Processing, 2020
• [MIA] Supervised Graph Hashing for Histopathology Image Retrieval and Classification
  • Xiaoshuang Shi, Fuyong Xing, Kaidi Xu, Yuanpu Xie, Hai Su, Lin Yang
  • Medical Image Analysis, 2017