Timezone: »
The existence of adversarial examples poses concerns for the robustness of convolutional neural networks (CNN), for which a popular hypothesis is about the frequency bias phenomenon: CNNs rely more on high-frequency components (HFC) for classification than humans, which causes the brittleness of CNNs. However, most previous works manually select and roughly divide the image frequency spectrum and conduct qualitative analysis. In this work, we introduce Shapley value, a metric of cooperative game theory, into the frequency domain and propose to quantify the positive (negative) impact of every frequency component of data on CNNs. Based on the Shapley value, we quantify the impact in a fine-grained way and show intriguing instance disparity. Statistically, we investigate adversarial training(AT) and the adversarial attack in the frequency domain. The observations motivate us to perform an in-depth analysis and lead to multiple novel hypotheses about i) the cause of adversarial robustness of the AT model; ii) the fairness problem of AT between different classes in the same dataset; iii) the attack bias on different frequency components. Finally, we propose a Shapley-value guided data augmentation technique for improving the robustness. Experimental results on image classification benchmarks show its effectiveness.
Author Information
Yiting Chen (Shanghai Jiao Tong University)
Qibing Ren (Shanghai Jiao Tong University)
Junchi Yan (Shanghai Jiao Tong University)
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: Rethinking and Improving Robustness of Convolutional Neural Networks: a Shapley Value-based Approach in Frequency Domain »
Wed. Nov 30th through Dec 1st Room Hall J #236
More from the Same Authors
-
2022 Poster: Improving Generative Adversarial Networks via Adversarial Learning in Latent Space »
Yang Li · Yichuan Mo · Liangliang Shi · Junchi Yan -
2022 Poster: ZARTS: On Zero-order Optimization for Neural Architecture Search »
Xiaoxing Wang · Wenxuan Guo · Jianlin Su · Xiaokang Yang · Junchi Yan -
2022 Poster: Learning Substructure Invariance for Out-of-Distribution Molecular Representations »
Nianzu Yang · Kaipeng Zeng · Qitian Wu · Xiaosong Jia · Junchi Yan -
2022 Spotlight: Lightning Talks 5B-3 »
Yanze Wu · Jie Xiao · Nianzu Yang · Jieyi Bi · Jian Yao · Yiting Chen · Qizhou Wang · Yangru Huang · Yongqiang Chen · Peixi Peng · Yuxin Hong · Xintao Wang · Feng Liu · Yining Ma · Qibing Ren · Xueyang Fu · Yonggang Zhang · Kaipeng Zeng · Jiahai Wang · GEN LI · Yonggang Zhang · Qitian Wu · Yifan Zhao · Chiyu Wang · Junchi Yan · Feng Wu · Yatao Bian · Xiaosong Jia · Ying Shan · Zhiguang Cao · Zheng-Jun Zha · Guangyao Chen · Tianjun Xiao · Han Yang · Jing Zhang · Jinbiao Chen · MA Kaili · Yonghong Tian · Junchi Yan · Chen Gong · Tong He · Binghui Xie · Yuan Sun · Francesco Locatello · Tongliang Liu · Yeow Meng Chee · David P Wipf · Tongliang Liu · Bo Han · Bo Han · Yanwei Fu · James Cheng · Zheng Zhang -
2022 Spotlight: Lightning Talks 5A-2 »
Qiang LI · Zhiwei Xu · Jiaqi Yang · Thai Hung Le · Haoxuan Qu · Yang Li · Artyom Sorokin · Peirong Zhang · Mira Finkelstein · Nitsan levy · Chung-Yiu Yau · dapeng li · Thommen Karimpanal George · De-Chuan Zhan · Nazar Buzun · Jiajia Jiang · Li Xu · Yichuan Mo · Yujun Cai · Yuliang Liu · Leonid Pugachev · Bin Zhang · Lucy Liu · Hoi-To Wai · Liangliang Shi · Majid Abdolshah · Yoav Kolumbus · Lin Geng Foo · Junchi Yan · Mikhail Burtsev · Lianwen Jin · Yuan Zhan · Dung Nguyen · David Parkes · Yunpeng Baiia · Jun Liu · Kien Do · Guoliang Fan · Jeffrey S Rosenschein · Sunil Gupta · Sarah Keren · Svetha Venkatesh -
2022 Spotlight: Improving Generative Adversarial Networks via Adversarial Learning in Latent Space »
Yang Li · Yichuan Mo · Liangliang Shi · Junchi Yan -
2022 Spotlight: Learning Substructure Invariance for Out-of-Distribution Molecular Representations »
Nianzu Yang · Kaipeng Zeng · Qitian Wu · Xiaosong Jia · Junchi Yan -
2022 Spotlight: NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification »
Qitian Wu · Wentao Zhao · Zenan Li · David P Wipf · Junchi Yan -
2022 Spotlight: Lightning Talks 1B-1 »
Qitian Wu · Runlin Lei · Rongqin Chen · Luca Pinchetti · Yangze Zhou · Abhinav Kumar · Hans Hao-Hsun Hsu · Wentao Zhao · Chenhao Tan · Zhen Wang · Shenghui Zhang · Yuesong Shen · Tommaso Salvatori · Gitta Kutyniok · Zenan Li · Amit Sharma · Leong Hou U · Yordan Yordanov · Christian Tomani · Bruno Ribeiro · Yaliang Li · David P Wipf · Daniel Cremers · Bolin Ding · Beren Millidge · Ye Li · Yuhang Song · Junchi Yan · Zhewei Wei · Thomas Lukasiewicz -
2022 Poster: NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification »
Qitian Wu · Wentao Zhao · Zenan Li · David P Wipf · Junchi Yan -
2022 Poster: Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks »
Chenxiao Yang · Qitian Wu · Junchi Yan -
2022 Poster: GraphDE: A Generative Framework for Debiased Learning and Out-of-Distribution Detection on Graphs »
Zenan Li · Qitian Wu · Fan Nie · Junchi Yan -
2022 Poster: The Policy-gradient Placement and Generative Routing Neural Networks for Chip Design »
Ruoyu Cheng · Xianglong Lyu · Yang Li · Junjie Ye · Jianye Hao · Junchi Yan -
2022 Poster: Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment »
Chenxiao Yang · Qitian Wu · Qingsong Wen · Zhiqiang Zhou · Liang Sun · Junchi Yan -
2022 Poster: Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline »
Penghao Wu · Xiaosong Jia · Li Chen · Junchi Yan · Hongyang Li · Yu Qiao -
2022 Poster: GraphQNTK: Quantum Neural Tangent Kernel for Graph Data »
Yehui Tang · Junchi Yan -
2021 Poster: Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness »
Jie Ren · Die Zhang · Yisen Wang · Lu Chen · Zhanpeng Zhou · Yiting Chen · Xu Cheng · Xin Wang · Meng Zhou · Jie Shi · Quanshi Zhang -
2020 Poster: Graduated Assignment for Joint Multi-Graph Matching and Clustering with Application to Unsupervised Graph Matching Network Learning »
Runzhong Wang · Junchi Yan · Xiaokang Yang -
2020 Poster: The Diversified Ensemble Neural Network »
Shaofeng Zhang · Meng Liu · Junchi Yan -
2020 Poster: Adversarial Learning for Robust Deep Clustering »
Xu Yang · Cheng Deng · Kun Wei · Junchi Yan · Wei Liu -
2019 Poster: Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling »
Qitian Wu · Zixuan Zhang · Xiaofeng Gao · Junchi Yan · Guihai Chen -
2018 Poster: Generalizing Graph Matching beyond Quadratic Assignment Model »
Tianshu Yu · Junchi Yan · Yilin Wang · Wei Liu · baoxin Li