Adversarial Learning

Morié Attack (MA): A New Potential Risk of Screen Photos NeurIPS 2021 Multi-Frame Recurrent Adversarial Network for Moving Object Segmentation WACV 2021 Multi-granularity Textual Adversarial Attack with Behavior Cloning EMNLP 2021 Multi-Layer Random Perturbation Training for improving Model Generalization Efficiently EMNLP 2021 Multi-SpectroGAN: High-Diversity and High-Fidelity Spectrogram Generation with Adversarial Style Combination for Speech Synthesis AAAI 2021 Multi-Target Adversarial Frameworks for Domain Adaptation in Semantic Segmentation ICCV 2021 Natural Adversarial Examples CVPR 2021 Navigating the GAN Parameter Space for Semantic Image Editing CVPR 2021 Neural Population Geometry Reveals the Role of Stochasticity in Robust Perception NeurIPS 2021 Neural Tangent Generalization Attacks ICML 2021 Not Just Compete, but Collaborate: Local Image-to-Image Translation via Cooperative Mask Prediction CVPR 2021 On Characterizing GAN Convergence Through Proximal Duality Gap ICML 2021 ONION: A Simple and Effective Defense Against Textual Backdoor Attacks EMNLP 2021 Online Class-Incremental Continual Learning with Adversarial Shapley Value AAAI 2021 On the Algorithmic Stability of Adversarial Training NeurIPS 2021 On the Convergence of Prior-Guided Zeroth-Order Optimization Algorithms NeurIPS 2021 On the Efficacy of Adversarial Data Collection for Question Answering: Results from a Large-Scale Randomized Study ACL 2021 On the Privacy Properties of GAN-generated Samples AISTATS 2021 On the Transferability of Adversarial Attacks against Neural Text Classifier EMNLP 2021 Over-the-Air Adversarial Flickering Attacks Against Video Recognition Networks CVPR 2021 Pairing Weak with Strong: Twin Models for Defending Against Adversarial Attack on Speaker Verification Interspeech 2021 Particle Cloud Generation with Message Passing Generative Adversarial Networks NeurIPS 2021 Partition-Guided GANs CVPR 2021 Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processing EMNLP 2021 PID-Based Approach to Adversarial Attacks AAAI 2021