← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Pushing the Right Buttons: Adversarial Evaluation of Quality Estimation EMNLP 2021
Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark EMNLP 2021
Investigating Robustness of Dialog Models to Popular Figurative Language Constructs EMNLP 2021
Learning with Safety Constraints: Sample Complexity of Reinforcement Learning for Constrained MDPs AAAI 2021
Transfer Learning for Efficient Iterative Safety Validation AAAI 2021
Sample-Specific Output Constraints for Neural Networks AAAI 2021
SMT-based Safety Checking of Parameterized Multi-Agent Systems AAAI 2021
Initiative Defense against Facial Manipulation AAAI 2021
Probabilistic Robustness Quantification of Neural Networks AAAI 2021
Safety Assurance for Systems with Machine Learning Components AAAI 2021
Verification and Repair of Neural Networks AAAI 2021
Adversarial Training and Provable Robustness: A Tale of Two Objectives AAAI 2021
Fast Training of Provably Robust Neural Networks by SingleProp AAAI 2021
Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification AAAI 2021
Model-Targeted Poisoning Attacks with Provable Convergence ICML 2021
Gaussian Process-Based Real-Time Learning for Safety Critical Applications ICML 2021
Query Complexity of Adversarial Attacks ICML 2021
Accelerating Safe Reinforcement Learning with Constraint-mismatched Baseline Policies ICML 2021
Safe Reinforcement Learning Using Advantage-Based Intervention ICML 2021
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization ICML 2021
Multi-Expert Adversarial Attack Detection in Person Re-Identification Using Context Inconsistency ICCV 2021
Aha! Adaptive History-Driven Attack for Decision-Based Black-Box Models ICCV 2021
HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training With Crafted Input Noise ICCV 2021
CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks ICCV 2021
Defending Against Universal Adversarial Patches by Clipping Feature Norms ICCV 2021