Adversarial Learning

Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch NeurIPS 2022 Sound Adversarial Audio-Visual Navigation ICLR 2022 Sparse-RS: A Versatile Framework for Query-Efficient Sparse Black-Box Adversarial Attacks AAAI 2022 Stability Analysis and Generalization Bounds of Adversarial Training NeurIPS 2022 Stereoscopic Universal Perturbations Across Different Architectures and Datasets CVPR 2022 Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability CVPR 2022 Student Surpasses Teacher: Imitation Attack for Black-Box NLP APIs COLING 2022 Style Agnostic 3D Reconstruction via Adversarial Style Transfer WACV 2022 Subspace Adversarial Training CVPR 2022 Synergy-of-Experts: Collaborate to Improve Adversarial Robustness NeurIPS 2022 TABS: Efficient Textual Adversarial Attack for Pre-trained NL Code Model Using Semantic Beam Search EMNLP 2022 TASA: Deceiving Question Answering Models by Twin Answer Sentences Attack EMNLP 2022 TextHacker: Learning based Hybrid Local Search Algorithm for Text Hard-label Adversarial Attack EMNLP 2022 TextHoaxer: Budgeted Hard-Label Adversarial Attacks on Text AAAI 2022 Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks EMNLP 2022 “That Is a Suspicious Reaction!”: Interpreting Logits Variation to Detect NLP Adversarial Attacks ACL 2022 Toward Efficient Robust Training against Union of ℓ_p Threat Models NeurIPS 2022 Towards Adversarially Robust Text Classifiers by Learning to Reweight Clean Examples ACL 2022 Towards Efficient Data Free Black-Box Adversarial Attack CVPR 2022 Towards Lightweight Black-Box Attack Against Deep Neural Networks NeurIPS 2022 Towards Transferable Adversarial Attacks on Vision Transformers AAAI 2022 Towards Understanding Adversarial Robustness of Optical Flow Networks CVPR 2022 Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NeurIPS 2022 TRAttack: Text Rewriting Attack Against Text Retrieval ACL 2022 Triggerless Backdoor Attack for NLP Tasks with Clean Labels NAACL 2022