Adversarial Learning

DeHiB: Deep Hidden Backdoor Attack on Semi-supervised Learning via Adversarial Perturbation AAAI 2021 Delving into Data: Effectively Substitute Training for Black-box Attack CVPR 2021 Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity IJCAI 2021 Don’t Search for a Search Method — Simple Heuristics Suffice for Adversarial Text Attacks EMNLP 2021 Double-Win Quant: Aggressively Winning Robustness of Quantized Deep Neural Networks via Random Precision Training and Inference ICML 2021 Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks NeurIPS 2021 Efficient Certification of Spatial Robustness AAAI 2021 Elastic Graph Neural Networks ICML 2021 Enhancing Robustness of Neural Networks through Fourier Stabilization ICML 2021 Enhancing the Transferability of Adversarial Attacks Through Variance Tuning CVPR 2021 Error-Correcting Output Codes with Ensemble Diversity for Robust Learning in Neural Networks AAAI 2021 Evaluating Deception Detection Model Robustness To Linguistic Variation NAACL 2021 Excess Capacity and Backdoor Poisoning NeurIPS 2021 Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption AAAI 2021 Exposing Cyber-Physical System Weaknesses by Implicitly Learning their Underlying Models ACML 2021 Fast Training of Provably Robust Neural Networks by SingleProp AAAI 2021 Feature Space Targeted Attacks by Statistic Alignment IJCAI 2021 Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks NeurIPS 2021 GANSpeech: Adversarial Training for High-Fidelity Multi-Speaker Speech Synthesis Interspeech 2021 Generalised Lipschitz Regularisation Equals Distributional Robustness ICML 2021 Generating Adversarial yet Inconspicuous Patches with a Single Image (Student Abstract) AAAI 2021 Generating Deep Networks Explanations with Robust Attribution Alignment ACML 2021 Generating Natural Language Attacks in a Hard Label Black Box Setting AAAI 2021 Globally-Robust Neural Networks ICML 2021 Glow-WaveGAN: Learning Speech Representations from GAN-Based Variational Auto-Encoder for High Fidelity Flow-Based Speech Synthesis Interspeech 2021