adversarial robustness

Certified Robustness Against Natural Language Attacks by Causal Intervention ICML 2022 Certified Robustness for Deep Equilibrium Models via Interval Bound Propagation ICLR 2022 Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations IJCAI 2022 Chunking Defense for Adversarial Attacks on ASR Interspeech 2022 Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers CVPR 2022 Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds NeurIPS 2022 Consistency Regularization for Adversarial Robustness AAAI 2022 Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks ICML 2022 Coordinated Attacks against Contextual Bandits: Fundamental Limits and Defense Mechanisms ICML 2022 CoPur: Certifiably Robust Collaborative Inference via Feature Purification NeurIPS 2022 Corruption-robust Offline Reinforcement Learning AISTATS 2022 Critical Perspectives: A Benchmark Revealing Pitfalls in PerspectiveAPI EMNLP 2022 Cross-Domain Detection of GPT-2-Generated Technical Text NAACL 2022 Data-Efficient Double-Win Lottery Tickets from Robust Pre-training ICML 2022 DDDM: A Brain-Inspired Framework for Robust Classification IJCAI 2022 Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal NeurIPS 2022 Defending Against Adversarial Attacks via Neural Dynamic System NeurIPS 2022 Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-Supervision AAAI 2022 Defensive Patches for Robust Recognition in the Physical World CVPR 2022 Demystifying the Adversarial Robustness of Random Transformation Defenses ICML 2022 Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations ACL 2022 Distinguishing Non-natural from Natural Adversarial Samples for More Robust Pre-trained Language Model ACL 2022 Diversified Adversarial Attacks based on Conjugate Gradient Method ICML 2022 Don’t sweat the small stuff, classify the rest: Sample Shielding to protect text classifiers against adversarial attacks NAACL 2022 Double Sampling Randomized Smoothing ICML 2022