← Core AI
Artificial Intelligence › Core AI ›

Adversarial Learning

1235 directly classified papers

Papers per year

Papers

Can Adversarial Training Be Manipulated By Non-Robust Features? NIPS 2022
Toward Efficient Robust Training against Union of $\ell_p$ Threat Models NIPS 2022
Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples NIPS 2022
A2: Efficient Automated Attacker for Boosting Adversarial Training NIPS 2022
Improving Adversarial Robustness via Mutual Information Estimation ICML 2022
Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning NIPS 2022
One-shot Neural Backdoor Erasing via Adversarial Weight Masking NIPS 2022
Gradient Methods Provably Converge to Non-Robust Networks NIPS 2022
Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspective NIPS 2022
Towards Lightweight Black-Box Attack Against Deep Neural Networks NIPS 2022
Adversarially Regularized Policy Learning Guided by Trajectory Optimization L4DC 2022
Certified Robustness Against Natural Language Attacks by Causal Intervention ICML 2022
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch NIPS 2022
Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity NIPS 2022
Learning to Generate Inversion-Resistant Model Explanations NIPS 2022
Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimization ICML 2022
Building Robust Ensembles via Margin Boosting ICML 2022
A Branch and Bound Framework for Stronger Adversarial Attacks of ReLU Networks ICML 2022
Stability Analysis and Generalization Bounds of Adversarial Training NIPS 2022
GAMA: Generative Adversarial Multi-Object Scene Attacks NIPS 2022
Make Some Noise: Reliable and Efficient Single-Step Adversarial Training NIPS 2022
Evolution of Neural Tangent Kernels under Benign and Adversarial Training NIPS 2022
TRAttack: Text Rewriting Attack Against Text Retrieval ACL 2022
Detecting Word-Level Adversarial Text Attacks via SHapley Additive exPlanations ACL 2022
Improving the Adversarial Robustness of NLP Models by Information Bottleneck ACL 2022