Artificial Intelligence › Core AI ›

AI Safety

2972 directly classified papers

Papers per year

Papers

Robot Reinforcement Learning on the Constraint Manifold CORL 2021

Assisted Robust Reward Design CORL 2021

Look Before You Leap: Safe Model-Based Reinforcement Learning with Human Intervention CORL 2021

On exploration requirements for learning safety constraints L4DC 2021

Exploiting Sparsity for Neural Network Verification L4DC 2021

Safely Learning Dynamical Systems from Short Trajectories L4DC 2021

Scalable Memory Protection in the PENGLAI Enclave OSDI 2021

Excess Capacity and Backdoor Poisoning NIPS 2021

Manipulating SGD with Data Ordering Attacks NIPS 2021

Center Smoothing: Certified Robustness for Networks with Structured Outputs NIPS 2021

Accumulative Poisoning Attacks on Real-time Data NIPS 2021

Towards Evaluating and Training Verifiably Robust Neural Networks CVPR 2021

Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink CVPR 2021

Robust Bayesian Neural Networks by Spectral Expectation Bound Regularization CVPR 2021

How Robust Are Randomized Smoothing Based Defenses to Data Poisoning? CVPR 2021

Improving the Transferability of Adversarial Samples With Adversarial Transformations CVPR 2021

Backdoor Attacks Against Deep Learning Systems in the Physical World CVPR 2021

LiBRe: A Practical Bayesian Approach to Adversarial Detection CVPR 2021

Reliability Testing for Natural Language Processing Systems ACL 2021

An Empirical Study on Adversarial Attack on NMT: Languages and Positions Matter ACL 2021

Closing the BIG-LID: An Effective Local Intrinsic Dimensionality Defense for Nonlinear Regression Poisoning IJCAI 2021

Towards Reducing Biases in Combining Multiple Experts Online IJCAI 2021

Automatically Exposing Problems with Neural Dialog Models EMNLP 2021

BFClass: A Backdoor-free Text Classification Framework EMNLP 2021

Fooling Thermal Infrared Pedestrian Detectors in Real World Using Small Bulbs AAAI 2021