← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs ACML 2022
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning NIPS 2022
Evolution of Neural Tangent Kernels under Benign and Adversarial Training NIPS 2022
Decision-based Black-box Attack Against Vision Transformers via Patch-wise Adversarial Removal NIPS 2022
Error Amplification When Updating Deployed Machine Learning Models MLHC 2022
Why predicting risk can’t identify ‘risk factors’: empirical assessment of model stability in machine learning across observational health databases MLHC 2022
Increasing Confidence in Adversarial Robustness Evaluations NIPS 2022
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022
Transferable 3D Adversarial Textures Using End-to-End Optimization WACV 2022
Universal Evasion Attacks on Summarization Scoring EMNLP 2022
When to Make Exceptions: Exploring Language Models as Accounts of Human Moral Judgment NIPS 2022
LOT: Layer-wise Orthogonal Training on Improving l2 Certified Robustness NIPS 2022
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective NIPS 2022
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks NIPS 2022
Your Out-of-Distribution Detection Method is Not Robust! NIPS 2022
Can Adversarial Training Be Manipulated By Non-Robust Features? NIPS 2022
Characteristics of Harmful Text: Towards Rigorous Benchmarking of Language Models NIPS 2022
Capturing Failures of Large Language Models via Human Cognitive Biases NIPS 2022
Weight Perturbation as Defense against Adversarial Word Substitutions EMNLP 2022
Safety Guarantees for Neural Network Dynamic Systems via Stochastic Barrier Functions NIPS 2022
Detecting textual adversarial examples through randomized substitution and vote UAI 2022
Data dependent randomized smoothing UAI 2022
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks NIPS 2021
Anti-Backdoor Learning: Training Clean Models on Poisoned Data NIPS 2021
Adversarial Neuron Pruning Purifies Backdoored Deep Models NIPS 2021