AI Safety

Adversarial Attack on Attackers: Post-Process to Mitigate Black-Box Score-Based Query Attacks NeurIPS 2022 Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs ACML 2022 Adversarially Robust Stability Certificates can be Sample-Efficient L4DC 2022 Adversarial Robustness Guarantees for Gaussian Processes JMLR 2022 Adversarial Robustness Through the Lens of Causality ICLR 2022 Adversarial training for high-stakes reliability NeurIPS 2022 Adversarial Unlearning of Backdoors via Implicit Hypergradient ICLR 2022 Aligning to Social Norms and Values in Interactive Narratives NAACL 2022 A Model Selection Approach for Corruption Robust Reinforcement Learning ALT 2022 Analyzing the Real Vulnerability of Hate Speech Detection Systems against Targeted Intentional Noise COLING 2022 An Equivalence Between Data Poisoning and Byzantine Gradient Attacks ICML 2022 Are AlphaZero-like Agents Robust to Adversarial Perturbations? NeurIPS 2022 Are You Stealing My Model? Sample Correlation for Fingerprinting Deep Neural Networks NeurIPS 2022 A Study of the Attention Abnormality in Trojaned BERTs NAACL 2022 Attacking deep networks with surrogate-based adversarial black-box methods is easy ICLR 2022 A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks NeurIPS 2022 A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network Interspeech 2022 Authentic Integration of Ethics and AI through Sociotechnical, Problem-Based Learning AAAI 2022 Automatic Reliability Testing For Cluster Management Controllers OSDI 2022 Automatic Termination for Hyperparameter Optimization AutoML 2022 A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Prediction NAACL 2022 Backdoor Attacks on the DNN Interpretation System AAAI 2022 BackdoorBench: A Comprehensive Benchmark of Backdoor Learning NeurIPS 2022 Barrier Bayesian Linear Regression: Online Learning of Control Barrier Conditions for Safety-Critical Control of Uncertain Systems L4DC 2022 Better Trigger Inversion Optimization in Backdoor Scanning CVPR 2022