Timezone: »
Adversarial training methods, which minimizes the loss of adversarially-perturbed training examples, have been extensively studied as a solution to improve the robustness of the deep neural networks. However, most adversarial training methods treat all training examples equally, while each example may have a different impact on the model's robustness during the course of training. Recent works have exploited such unequal importance of adversarial samples to model's robustness, which has been shown to obtain high robustness against untargeted PGD attacks. However, we empirically observe that they make the feature spaces of adversarial samples across different classes overlap, and thus yield more high-entropy samples whose labels could be easily flipped. This makes them more vulnerable to targeted adversarial perturbations. Moreover, to address such limitations, we propose a simple yet effective weighting scheme, Entropy-Weighted Adversarial Training (EWAT), which weighs the loss for each adversarial training example proportionally to the entropy of its predicted distribution, to focus on examples whose labels are more uncertain. We validate our method on multiple benchmark datasets and show that it achieves an impressive increase of robust accuracy.
Author Information
Minseon Kim (Korea Advanced Institute of Science and Technology)
Jihoon Tack (KAIST)
Jinwoo Shin (KAIST)
Sung Ju Hwang (UNIST)
More from the Same Authors
-
2021 : SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Adversarial Robustness »
Jongheon Jeong · Sejun Park · Minkyu Kim · Heung-Chang Lee · Doguk Kim · Jinwoo Shin -
2021 : Consistency Regularization for Adversarial Robustness »
Jihoon Tack · Sihyun Yu · Jongheon Jeong · Minseon Kim · Sung Ju Hwang · Jinwoo Shin -
2023 : Few-shot Anomaly Detection via Personalization »
Sangkyung Kwak · Jongheon Jeong · Hankook Lee · Woohyuck Kim · Jinwoo Shin -
2023 : Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations »
Hyeonjeong Ha · Minseon Kim · Sung Ju Hwang -
2023 : Bias-to-Text: Debiasing Unknown Visual Biases by Language Interpretation »
Younghyun Kim · Sangwoo Mo · Minkyu Kim · Kyungmin Lee · Jaeho Lee · Jinwoo Shin -
2023 : Breaking the Spurious Causality of Conditional Generation via Fairness Intervention with Corrective Sampling »
Jun Hyun Nam · Sangwoo Mo · Jaeho Lee · Jinwoo Shin -
2023 : Guide Your Agent with Adaptive Multimodal Rewards »
Changyeon Kim · Younggyo Seo · Hao Liu · Lisa Lee · Jinwoo Shin · Honglak Lee · Kimin Lee -
2023 : Collaborative Score Distillation for Consistent Visual Synthesis »
Subin Kim · Kyungmin Lee · June Suk Choi · Jongheon Jeong · Kihyuk Sohn · Jinwoo Shin -
2023 : Semi-supervised Tabular Classification via In-context Learning of Large Language Models »
Jaehyun Nam · Woomin Song · Seong Hyeon Park · Jihoon Tack · Sukmin Yun · Jaehyung Kim · Jinwoo Shin -
2023 : Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models »
Sanghyun Kim · Seohyeon Jung · Balhae Kim · Moonseok Choi · Jinwoo Shin · Juho Lee -
2023 Poster: Prefer to Classify: Improving Text Classifiers via Auxiliary Preference Learning »
Jaehyung Kim · Jinwoo Shin · Dongyeop Kang -
2023 Poster: Modality-Agnostic Variational Compression of Implicit Neural Representations »
Jonathan Richard Schwarz · Jihoon Tack · Yee-Whye Teh · Jaeho Lee · Jinwoo Shin -
2023 Poster: Personalized Subgraph Federated Learning »
Jinheon Baek · Wonyong Jeong · Jiongdao Jin · Jaehong Yoon · Sung Ju Hwang -
2023 Poster: Exploring Chemical Space with Score-based Out-of-distribution Generation »
Seul Lee · Jaehyeong Jo · Sung Ju Hwang -
2023 Poster: Continual Learners are Incremental Model Generalizers »
Jaehong Yoon · Sung Ju Hwang · Yue Cao -
2023 Poster: Scalable Set Encoding with Universal Mini-Batch Consistency and Unbiased Full Set Gradient Approximation »
Jeffrey Willette · Seanie Lee · Bruno Andreis · Kenji Kawaguchi · Juho Lee · Sung Ju Hwang -
2023 Poster: Multi-View Masked World Models for Visual Robotic Manipulation »
Younggyo Seo · Junsu Kim · Stephen James · Kimin Lee · Jinwoo Shin · Pieter Abbeel -
2023 Poster: Margin-based Neural Network Watermarking »
Byungjoo Kim · Suyoung Lee · Seanie Lee · Son · Sung Ju Hwang -
2022 Poster: TSPipe: Learn from Teacher Faster with Pipelines »
Hwijoon Lim · Yechan Kim · Sukmin Yun · Jinwoo Shin · Dongsu Han -
2022 Spotlight: TSPipe: Learn from Teacher Faster with Pipelines »
Hwijoon Lim · Yechan Kim · Sukmin Yun · Jinwoo Shin · Dongsu Han -
2022 Poster: Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning »
Kyunghwan Son · Junsu Kim · Sungsoo Ahn · Roben Delos Reyes · Yung Yi · Jinwoo Shin -
2022 Poster: Time Is MattEr: Temporal Self-supervision for Video Transformers »
Sukmin Yun · Jaehyung Kim · Dongyoon Han · Hwanjun Song · Jung-Woo Ha · Jinwoo Shin -
2022 Spotlight: Disentangling Sources of Risk for Distributional Multi-Agent Reinforcement Learning »
Kyunghwan Son · Junsu Kim · Sungsoo Ahn · Roben Delos Reyes · Yung Yi · Jinwoo Shin -
2022 Spotlight: Time Is MattEr: Temporal Self-supervision for Video Transformers »
Sukmin Yun · Jaehyung Kim · Dongyoon Han · Hwanjun Song · Jung-Woo Ha · Jinwoo Shin -
2021 : Contributed Talk #6 »
Jihoon Tack -
2021 : Contrastive Learning for Novelty Detection »
Jinwoo Shin -
2021 Poster: Self-Improved Retrosynthetic Planning »
Junsu Kim · Sungsoo Ahn · Hankook Lee · Jinwoo Shin -
2021 Spotlight: Self-Improved Retrosynthetic Planning »
Junsu Kim · Sungsoo Ahn · Hankook Lee · Jinwoo Shin -
2021 Poster: Learning to Generate Noise for Multi-Attack Robustness »
Divyam Madaan · Jinwoo Shin · Sung Ju Hwang -
2021 Spotlight: Learning to Generate Noise for Multi-Attack Robustness »
Divyam Madaan · Jinwoo Shin · Sung Ju Hwang -
2021 Poster: State Entropy Maximization with Random Encoders for Efficient Exploration »
Younggyo Seo · Lili Chen · Jinwoo Shin · Honglak Lee · Pieter Abbeel · Kimin Lee -
2021 Spotlight: State Entropy Maximization with Random Encoders for Efficient Exploration »
Younggyo Seo · Lili Chen · Jinwoo Shin · Honglak Lee · Pieter Abbeel · Kimin Lee -
2020 Poster: Self-supervised Label Augmentation via Input Transformations »
Hankook Lee · Sung Ju Hwang · Jinwoo Shin -
2020 Poster: Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning »
Kimin Lee · Younggyo Seo · Seunghyun Lee · Honglak Lee · Jinwoo Shin -
2020 Poster: Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix »
Insu Han · Haim Avron · Jinwoo Shin -
2020 Poster: Learning What to Defer for Maximum Independent Sets »
Sungsoo Ahn · Younggyo Seo · Jinwoo Shin -
2020 Poster: Adversarial Neural Pruning with Latent Vulnerability Suppression »
Divyam Madaan · Jinwoo Shin · Sung Ju Hwang -
2019 Poster: Spectral Approximate Inference »
Sejun Park · Eunho Yang · Se-Young Yun · Jinwoo Shin -
2019 Poster: Robust Inference via Generative Classifiers for Handling Noisy Labels »
Kimin Lee · Sukmin Yun · Kibok Lee · Honglak Lee · Bo Li · Jinwoo Shin -
2019 Poster: Learning What and Where to Transfer »
Yunhun Jang · Hankook Lee · Sung Ju Hwang · Jinwoo Shin -
2019 Oral: Spectral Approximate Inference »
Sejun Park · Eunho Yang · Se-Young Yun · Jinwoo Shin -
2019 Oral: Robust Inference via Generative Classifiers for Handling Noisy Labels »
Kimin Lee · Sukmin Yun · Kibok Lee · Honglak Lee · Bo Li · Jinwoo Shin -
2019 Oral: Learning What and Where to Transfer »
Yunhun Jang · Hankook Lee · Sung Ju Hwang · Jinwoo Shin -
2019 Poster: Training CNNs with Selective Allocation of Channels »
Jongheon Jeong · Jinwoo Shin -
2019 Oral: Training CNNs with Selective Allocation of Channels »
Jongheon Jeong · Jinwoo Shin -
2018 Poster: Bucket Renormalization for Approximate Inference »
Sungsoo Ahn · Michael Chertkov · Adrian Weller · Jinwoo Shin -
2018 Oral: Bucket Renormalization for Approximate Inference »
Sungsoo Ahn · Michael Chertkov · Adrian Weller · Jinwoo Shin -
2017 Poster: Faster Greedy MAP Inference for Determinantal Point Processes »
Insu Han · Prabhanjan Kambadur · Kyoungsoo Park · Jinwoo Shin -
2017 Poster: Confident Multiple Choice Learning »
Kimin Lee · Changho Hwang · KyoungSoo Park · Jinwoo Shin -
2017 Talk: Confident Multiple Choice Learning »
Kimin Lee · Changho Hwang · KyoungSoo Park · Jinwoo Shin -
2017 Talk: Faster Greedy MAP Inference for Determinantal Point Processes »
Insu Han · Prabhanjan Kambadur · Kyoungsoo Park · Jinwoo Shin