AI Safety

Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NeurIPS 2022 Transferable 3D Adversarial Textures Using End-to-End Optimization WACV 2022 Trigger Hunting with a Topological Prior for Trojan Detection ICLR 2022 Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022 UKP-SQuARE v2: Explainability and Adversarial Attacks for Trustworthy QA AACL 2022 Understanding and Improving Graph Injection Attack by Promoting Unnoticeability ICLR 2022 Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning IJCAI 2022 Universal Evasion Attacks on Summarization Scoring EMNLP 2022 Upstream Mitigation Is Not All You Need: Testing the Bias Transfer Hypothesis in Pre-Trained Language Models ACL 2022 User-Level Differential Privacy against Attribute Inference Attack of Speech Emotion Recognition on Federated Learning Interspeech 2022 Verification and Monitoring for First-Order LTL with Persistence-Preserving Quantification over Finite and Infinite Traces IJCAI 2022 Verification of Neural-Network Control Systems by Integrating Taylor Models and Zonotopes AAAI 2022 WeDef: Weakly Supervised Backdoor Defense for Text Classification EMNLP 2022 Weight Perturbation as Defense against Adversarial Word Substitutions EMNLP 2022 When Adversarial Training Meets Vision Transformers: Recipes from Training to Architecture NeurIPS 2022 When are Local Queries Useful for Robust Learning? NeurIPS 2022 When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment NeurIPS 2022 Where to Attack: A Dynamic Locator Model for Backdoor Attack in Text Classifications COLING 2022 Why predicting risk can’t identify ‘risk factors’: empirical assessment of model stability in machine learning across observational health databases MLHC 2022 Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power NeurIPS 2022 Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP EMNLP 2022 Your Out-of-Distribution Detection Method is Not Robust! NeurIPS 2022 Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies ICML 2021 Accumulative Poisoning Attacks on Real-time Data NeurIPS 2021 Achieving Proportionality up to the Maximin Item with Indivisible Goods AAAI 2021