← Core AI
Artificial Intelligence › Core AI ›

Adversarial Learning

1235 directly classified papers

Papers per year

Papers

Improving Robustness of Language Models from a Geometry-aware Perspective ACL 2022
Perturbations in the Wild: Leveraging Human-Written Text Perturbations for Realistic Adversarial Attack and Defense ACL 2022
Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples ACL 2022
Input-specific Attention Subnetworks for Adversarial Detection ACL 2022
RoCBert: Robust Chinese Bert with Multimodal Contrastive Pretraining ACL 2022
Neurotoxin: Durable Backdoors in Federated Learning ICML 2022
Understanding Robust Overfitting of Adversarial Training and Beyond ICML 2022
Diversified Adversarial Attacks based on Conjugate Gradient Method ICML 2022
Robust Deep Reinforcement Learning through Bootstrapped Opportunistic Curriculum ICML 2022
Removing Batch Normalization Boosts Adversarial Training ICML 2022
DeepFake Disrupter: The Detector of DeepFake Is My Friend CVPR 2022
DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints CVPR 2022
Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks With Implicit Gradients CVPR 2022
Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack CVPR 2022
Improving Adversarial Transferability via Neuron Attribution-Based Attacks CVPR 2022
Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart CVPR 2022
Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations CVPR 2022
Can You Spot the Chameleon? Adversarially Camouflaging Images From Co-Salient Object Detection CVPR 2022
Subspace Adversarial Training CVPR 2022
Backdoor Attacks on Self-Supervised Learning CVPR 2022
Exploring Frequency Adversarial Attacks for Face Forgery Detection CVPR 2022
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022
360-Attack: Distortion-Aware Perturbations From Perspective-Views CVPR 2022
Cross-Modal Transferable Adversarial Attacks From Images to Videos CVPR 2022
Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training CVPR 2022