Adversarial Training, Attacks, Denfense and Robustness

Adversarial Training

[2015 ICML] Unsupervised Domain Adaptation by Backpropagation, [paper], [bibtex], sources: [shucunt/domain_adaptation], [pumpikano/tf-dann], [kskdev/DANN], [fungtion/DANN].
[2016 JMLR] Domain-Adversarial Training of Neural Networks, [paper], [bibtex], sources: [shucunt/domain_adaptation], [pumpikano/tf-dann], [kskdev/DANN], [fungtion/DANN].
[2016 ICLR] Distributional Smoothing with Virtual Adversarial Training, [paper], [bibtex], sources: [takerum/vat_tf], [lyakaap/VAT-pytorch], [takerum/vat], [takerum/vat_chainer].
[2018 TPAMI] Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learning, [paper], [bibtex], [homepage], sources: [takerum/vat_tf], [lyakaap/VAT-pytorch], [takerum/vat], [takerum/vat_chainer].

Attacks

[2016 CVPR] DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks, [paper], [bibtex], sources: [LTS4/DeepFool].
[2017 ICLR] Delving into Transferable Adversarial Examples and Black-Box Attacks, [paper], [bibtex], sources: [sunblaze-ucb/transferability-advdnn-pub], [YuguangTong/transferability-advdnn-pub].
[2018 AAAI] EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples, [paper], [bibtex], sources: [IBM/EAD-Attack], [ysharma1126/EAD_Attack].
[2018 ICLR] Attacking Binarized Neural Networks, [paper], [bibtex], sources: [AngusG/cleverhans-attacking-bnns].
[2018 SPW] Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers, [paper], [bibtex], sources: [QData/deepWordBug].
[2018 ACL] HotFlip: White-Box Adversarial Examples for Text Classification, [paper], [poster], [bibtex], sources: [alicia-tsai/adversarial-sentiment-classification].
[2018 ArXiv] Adversarial Examples for Natural Language Classification Problems, [paper], [bibtex].
[2019 ICML] NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks, [paper], [bibtex], sources: [Cold-Winter/Nattack].
[2019 NDSS] TextBugger: Generating Adversarial Text Against Real-world Applications, [paper], [bibtex].
[2019 ACL] Generating Natural Language Adversarial Examples through Probability Weighted Word Saliency, [paper], [bibtex], sources: [JHL-HUST/PWWS].
[2020 AAAI] Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment, [paper], [bibtex], sources: [jind11/TextFooler].
[2020 ICLR] Query-Efficient Meta Attack to Deep Neural Networks, [paper], [bibtex], sources: [dydjw9/MetaAttack_ICLR2020].
[2021 CVPR] Can audio-visual integration strengthen robustness under multimodal attacks?, [paper], [bibtex], sources: [YapengTian/AV-Robustness-CVPR21].

Defenses

[2017 ICML] Detecting Adversarial Samples from Artifacts, [paper], [bibtex], sources: [rfeinman/detecting-adversarial-samples].
[2018 ICLR] Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality, [paper], [bibtex], sources: [xingjunm/lid_adversarial_subspace_detection].
[2018 ICLR] Towards Deep Learning Models Resistant to Adversarial Attacks, [paper], [bibtex].
[2018 ICLR] Defense-GAN: Protecting Classifier Against Adversarial Attacks Using Generative Models, [paper], [bibtex], sources: [kabkabm/defensegan].
[2018 EMNLP] Generating Natural Language Adversarial Examples, [paper], [bibtex], sources: [nesl/nlp_adversarial_examples].
[2019 ICLR] Improving the Generalization of Adversarial Training with Domain Adaptation, [paper], [bibtex], sources: [JHL-HUST/ATDA].
[2020 ICLR] Detecting and Diagnosing Adversarial Images with Class-Conditional Capsule Reconstructions, [paper], [bibtex].
[2020 ArXiv] RAIN: A Simple Framework for Robust and Accurate Image Classification, [paper], [bibtex].
[2021 ArXiv] Adversarial Visual Robustness by Causal Intervention, [paper], [bibtex], sources: [KaihuaTang/Adversarial-Robustness-by-Causal-Intervention.pytorch].