Adversarial Learning

Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations EMNLP 2022 Bi-Level Alignment for Cross-Domain Crowd Counting CVPR 2022 Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation NAACL 2022 Blackbox Attacks via Surrogate Ensemble Search NeurIPS 2022 Blindfolded Attackers Still Threatening: Strict Black-Box Adversarial Attacks on Graphs AAAI 2022 Boosting the Performance of Generic Deep Neural Network Frameworks with Log-supermodular CRFs NeurIPS 2022 Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation NeurIPS 2022 Boosting the Transferability of Video Adversarial Examples via Temporal Translation AAAI 2022 Bounded Adversarial Attack on Deep Content Features CVPR 2022 BppAttack: Stealthy and Efficient Trojan Attacks Against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning CVPR 2022 Bridging the Gap: Unifying the Training and Evaluation of Neural Network Binary Classifiers NeurIPS 2022 Building Robust Ensembles via Margin Boosting ICML 2022 Can Adversarial Training Be Manipulated By Non-Robust Features? NeurIPS 2022 Can You Spot the Chameleon? Adversarially Camouflaging Images From Co-Salient Object Detection CVPR 2022 CAT: Customized Adversarial Training for Improved Robustness IJCAI 2022 CC-CERT: A Probabilistic Approach to Certify General Robustness of Neural Networks AAAI 2022 Certified Adversarial Robustness Under the Bounded Support Set ICML 2022 Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations IJCAI 2022 Character-level White-Box Adversarial Attacks against Transformers via Attachable Subwords Substitution EMNLP 2022 Class-Aware Adversarial Transformers for Medical Image Segmentation NeurIPS 2022 Clothes-Changing Person Re-Identification With RGB Modality Only CVPR 2022 CLPA: Clean-Label Poisoning Availability Attacks Using Generative Adversarial Nets AAAI 2022 CMGAN: Conformer-based Metric GAN for Speech Enhancement Interspeech 2022 CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes AAAI 2022 CODE: Contrastive Pre-training with Adversarial Fine-Tuning for Zero-Shot Expert Linking AAAI 2022