Adversarial Learning

FrePGAN: Robust Deepfake Detection Using Frequency-Level Perturbations AAAI 2022 Frequency-Driven Imperceptible Adversarial Attack on Semantic Similarity CVPR 2022 GAMA: Generative Adversarial Multi-Object Scene Attacks NeurIPS 2022 Generating Authentic Adversarial Examples beyond Meaning-preserving with Doubly Round-trip Translation NAACL 2022 Generating Distributional Adversarial Examples to Evade Statistical Detectors ICML 2022 Gradient Methods Provably Converge to Non-Robust Networks NeurIPS 2022 GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing ICML 2022 Has CEO Gender Bias Really Been Fixed? Adversarial Attacking and Improving Gender Fairness in Image Search AAAI 2022 Hibernated Backdoor: A Mutual Information Empowered Backdoor Attack to Deep Neural Networks AAAI 2022 Imperceptible Backdoor Attack: From Input Space to Feature Representation IJCAI 2022 Improving Adversarial Robustness via Mutual Information Estimation ICML 2022 Improving Adversarial Transferability via Neuron Attribution-Based Attacks CVPR 2022 Improving Certified Robustness via Statistical Learning with Logical Reasoning NeurIPS 2022 Improving Robustness of Language Models from a Geometry-aware Perspective ACL 2022 Improving the Adversarial Robustness of NLP Models by Information Bottleneck ACL 2022 Improving Transferability of Adversarial Examples with Virtual Step and Auxiliary Gradients IJCAI 2022 Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples NeurIPS 2022 Input-specific Attention Subnetworks for Adversarial Detection ACL 2022 LCANets: Lateral Competition Improves Robustness Against Corruption and Attack ICML 2022 Learn2Weight: Parameter Adaptation against Similar-domain Adversarial Attacks COLING 2022 Learning to Generate Inversion-Resistant Model Explanations NeurIPS 2022 Learning Universal Adversarial Perturbation by Adversarial Example AAAI 2022 Leveraging Adversarial Examples To Quantify Membership Information Leakage CVPR 2022 Make Some Noise: Reliable and Efficient Single-Step Adversarial Training NeurIPS 2022 Making Adversarial Examples More Transferable and Indistinguishable AAAI 2022