Adversarial Learning

A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization ICML 2021 Backdoor Attacks Against Deep Learning Systems in the Physical World CVPR 2021 Backdoor Attack with Imperceptible Input and Latent Modification NeurIPS 2021 BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning IJCAI 2021 Basis-MelGAN: Efficient Neural Vocoder Based on Audio Decomposition Interspeech 2021 Batch Normalization Increases Adversarial Vulnerability and Decreases Adversarial Transferability: A Non-Robust Feature Perspective ICCV 2021 Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions AAAI 2021 BERT & Family Eat Word Salad: Experiments with Text Understanding AAAI 2021 Best of Both Worlds: Robust Accented Speech Recognition with Adversarial Transfer Learning Interspeech 2021 Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression EMNLP 2021 BFClass: A Backdoor-free Text Classification Framework EMNLP 2021 Bi-Classifier Determinacy Maximization for Unsupervised Domain Adaptation AAAI 2021 Bigram and Unigram Based Text Attack via Adaptive Monotonic Heuristic Search AAAI 2021 Blind Pareto Fairness and Subgroup Robustness ICML 2021 Blur, Noise, and Compression Robust Generative Adversarial Networks CVPR 2021 Boundary Knowledge Translation based Reference Semantic Segmentation IJCAI 2021 Building Reliable Explanations of Unreliable Neural Networks: Locally Smoothing Perspective of Model Interpretation CVPR 2021 calibrated adversarial training ACML 2021 Can we have it all? On the Trade-off between Spatial and Adversarial Robustness of Neural Networks NeurIPS 2021 Certified Robustness to Programmable Transformations in LSTMs EMNLP 2021 Characterizing the Evasion Attackability of Multi-label Classifiers AAAI 2021 CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection ICML 2021 Class-Disentanglement and Applications in Adversarial Detection and Defense NeurIPS 2021 Combinatorial Optimization for Panoptic Segmentation: A Fully Differentiable Approach NeurIPS 2021 Commonsense Knowledge Augmentation for Low-Resource Languages via Adversarial Learning AAAI 2021