AI Safety

Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations CVPR 2022 FLamby: Datasets and Benchmarks for Cross-Silo Federated Learning in Realistic Healthcare Settings NeurIPS 2022 Flooding-X: Improving BERT’s Resistance to Adversarial Attacks via Loss-Restricted Fine-Tuning ACL 2022 Foiling Training-Time Attacks on Neural Machine Translation Systems EMNLP 2022 GalilAI: Out-of-Task Distribution Detection using Causal Active Experimentation for Safe Transfer RL AISTATS 2022 Gaussian Process Uniform Error Bounds with Unknown Hyperparameters for Safety-Critical Applications ICML 2022 GoTube: Scalable Statistical Verification of Continuous-Depth Models AAAI 2022 Handcrafted Backdoors in Deep Neural Networks NeurIPS 2022 Hibernated Backdoor: A Mutual Information Empowered Backdoor Attack to Deep Neural Networks AAAI 2022 How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data ICLR 2022 How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective ICLR 2022 Imperceptible Backdoor Attack: From Input Space to Feature Representation IJCAI 2022 Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100 ICLR 2022 Improving Certified Robustness via Statistical Learning with Logical Reasoning NeurIPS 2022 Improving Robustness Against Stealthy Weight Bit-Flip Attacks by Output Code Matching CVPR 2022 Increasing Confidence in Adversarial Robustness Evaluations NeurIPS 2022 Information-Theoretic Safe Exploration with Gaussian Processes NeurIPS 2022 Input-Specific Robustness Certification for Randomized Smoothing AAAI 2022 Intriguing Properties of Input-Dependent Randomized Smoothing ICML 2022 Investigating Top-k White-Box and Transferable Black-Box Attack CVPR 2022 Investigations of Performance and Bias in Human-AI Teamwork in Hiring AAAI 2022 Joint Synthesis of Safety Certificate and Safe Control Policy Using Constrained Reinforcement Learning L4DC 2022 Language Model Detoxification in Dialogue with Contextualized Stance Control EMNLP 2022 Learning Optimal Conformal Classifiers ICLR 2022 Leashing the Inner Demons: Self-Detoxification for Language Models AAAI 2022