Adversarial Learning

How do humans perceive adversarial text? A reality check on the validity and naturalness of word-based adversarial attacks ACL 2023 How Many Perturbations Break This Model? Evaluating Robustness Beyond Adversarial Accuracy ICML 2023 How Reliable Are AI-Generated-Text Detectors? An Assessment Framework Using Evasive Soft Prompts EMNLP 2023 How to Backdoor Diffusion Models? CVPR 2023 How to Choose your Best Allies for a Transferable Attack? ICCV 2023 HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text NeurIPS 2023 Hypothetical Training for Robust Machine Reading Comprehension of Tabular Context ACL 2023 IBA: Towards Irreversible Backdoor Attacks in Federated Learning NeurIPS 2023 Identification of Systematic Errors of Image Classifiers on Rare Subgroups ICCV 2023 Identification of the Adversary from a Single Adversarial Example ICML 2023 ILA-DA: Improving Transferability of Intermediate Level Attack with Data Augmentation ICLR 2023 ImageNet Pre-training Also Transfers Non-robustness AAAI 2023 IMBERT: Making BERT Immune to Insertion-based Backdoor Attacks ACL 2023 Impact of Adversarial Training on Robustness and Generalizability of Language Models ACL 2023 Imperceptible Adversarial Attack via Invertible Neural Networks AAAI 2023 Improve Video Representation with Temporal Adversarial Augmentation IJCAI 2023 Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samples ICML 2023 Improving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics ICML 2023 Improving Adversarial Robustness Through the Contrastive-Guided Diffusion Process ICML 2023 Improving Adversarial Robustness to Sensitivity and Invariance Attacks with Deep Metric Learning (Student Abstract) AAAI 2023 Improving Adversarial Robustness via Joint Classification and Multiple Explicit Detection Classes AISTATS 2023 Improving Adversarial Robustness with Self-Paced Hard-Class Pair Reweighting AAAI 2023 Improving Adversarial Transferability via Intermediate-level Perturbation Decay NeurIPS 2023 Improving Classifier Robustness through Active Generative Counterfactual Data Augmentation EMNLP 2023 Improving Diversity With Adversarially Learned Transformations for Domain Generalization WACV 2023