Adversarial Learning

Adversarial training for high-stakes reliability NeurIPS 2022 Are AlphaZero-like Agents Robust to Adversarial Perturbations? NeurIPS 2022 A Study of the Attention Abnormality in Trojaned BERTs NAACL 2022 Attacking Video Recognition Models with Bullet-Screen Comments AAAI 2022 Attack on Unfair ToS Clause Detection: A Case Study using Universal Adversarial Triggers EMNLP 2022 Audio Anti-spoofing Using Simple Attention Module and Joint Optimization Based on Additive Angular Margin Loss and Meta-learning Interspeech 2022 A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks NeurIPS 2022 A Unified Framework for Adversarial Attack and Defense in Constrained Feature Space IJCAI 2022 A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network Interspeech 2022 Automatic Fake News Detection: Are current models “fact-checking” or“gut-checking”? ACL 2022 A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction NAACL 2022 Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling EMNLP 2022 Backdoor Attacks on Self-Supervised Learning CVPR 2022 Backdoor Attacks on the DNN Interpretation System AAAI 2022 BackdoorBench: A Comprehensive Benchmark of Backdoor Learning NeurIPS 2022 BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models ICLR 2022 BagFlip: A Certified Defense Against Data Poisoning NeurIPS 2022 Balanced Adversarial Training: Balancing Tradeoffs between Fickleness and Obstinacy in NLP Models EMNLP 2022 Bandits for Structure Perturbation-Based Black-Box Attacks To Graph Neural Networks With Theoretical Guarantees CVPR 2022 Blackbox Attacks via Surrogate Ensemble Search NeurIPS 2022 Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs AAAI 2022 Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation NeurIPS 2022 Boosting the Transferability of Video Adversarial Examples via Temporal Translation AAAI 2022 BppAttack: Stealthy and Efficient Trojan Attacks Against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning CVPR 2022 Building Robust Ensembles via Margin Boosting ICML 2022