← Core AI
Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Admix: Enhancing the Transferability of Adversarial Attacks ICCV 2021
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks ICCV 2021
Integer-Arithmetic-Only Certified Robustness for Quantized Neural Networks ICCV 2021
ProFlip: Targeted Trojan Attack With Progressive Bit Flips ICCV 2021
AdvRush: Searching for Adversarially Robust Neural Architectures ICCV 2021
AdvDrop: Adversarial Attack to DNNs by Dropping Information ICCV 2021
Towards Certifying L-infinity Robustness using Neural Networks with L-inf-dist Neurons ICML 2021
Globally-Robust Neural Networks ICML 2021
Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks ICML 2021
Inverse Constrained Reinforcement Learning ICML 2021
High Confidence Generalization for Reinforcement Learning ICML 2021
Reinforcement Learning Under Moral Uncertainty ICML 2021
Safe Reinforcement Learning with Linear Function Approximation ICML 2021
Sample Efficient Detection and Classification of Adversarial Attacks via Self-Supervised Embeddings ICCV 2021
Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models ICCV 2021
Data Efficient Algorithms and Interpretability Requirements for Personalized Assessment of Taskable AI Systems IJCAI 2021
DEEPSPLIT: An Efficient Splitting Method for Neural Network Verification via Indirect Effect Analysis IJCAI 2021
Justicia: A Stochastic SAT Approach to Formally Verify Fairness AAAI 2021
Preventing Repeated Real World AI Failures by Cataloging Incidents: The AI Incident Database AAAI 2021
Sequential Attacks on Kalman Filter-based Forward Collision Warning Systems AAAI 2021
DeHiB: Deep Hidden Backdoor Attack on Semi-supervised Learning via Adversarial Perturbation AAAI 2021
Inverse Reinforcement Learning From Like-Minded Teachers AAAI 2021
Robust Reinforcement Learning: A Case Study in Linear Quadratic Regulation AAAI 2021
Mitigating Political Bias in Language Models through Reinforced Calibration AAAI 2021
Certifying Incremental Quadratic Constraints for Neural Networks via Convex Optimization L4DC 2021