adversarial example

Structured Adversarial Attack: Towards General Implementation and Better Interpretability ICLR 2019 Subspace Attack: Exploiting Promising Subspaces for Query-Efficient Black-box Attacks NeurIPS 2019 The Limitations of Adversarial Training and the Blind-Spot Attack ICLR 2019 The Odds are Odd: A Statistical Test for Detecting Adversarial Examples ICML 2019 Theoretically Principled Trade-off between Robustness and Accuracy ICML 2019 Towards the first adversarially robust neural network model on MNIST ICLR 2019 Transferable Adversarial Attacks for Image and Video Object Detection IJCAI 2019 Understanding the Effect of Textual Adversaries in Multimodal Machine Translation EMNLP 2019 Universal Perturbation Attack Against Image Retrieval ICCV 2019 Using Pre-Training Can Improve Model Robustness and Uncertainty ICML 2019 Wasserstein Adversarial Examples via Projected Sinkhorn Iterations ICML 2019 White-to-Black: Efficient Distillation of Black-Box Adversarial Attacks NAACL 2019 Adversarial Example Generation with Syntactically Controlled Paraphrase Networks NAACL 2018 Adversarial Examples that Fool both Computer Vision and Time-Limited Humans NeurIPS 2018 Adversarially Regularising Neural NLI Models to Integrate Logical Background Knowledge CoNLL 2018 Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Models CoNLL 2018 Adversarial Risk and the Dangers of Evaluating Against Weak Attacks ICML 2018 Analyzing the Robustness of Nearest Neighbors to Adversarial Examples ICML 2018 Attacking Visual Language Grounding with Adversarial Examples: A Case Study on Neural Image Captioning ACL 2018 Black-box Adversarial Attacks with Limited Queries and Information ICML 2018 Certified Defenses against Adversarial Examples ICLR 2018 Certifying Some Distributional Robustness with Principled Adversarial Training ICLR 2018 Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality ICLR 2018 Constructing Unrestricted Adversarial Examples with Generative Models NeurIPS 2018 Countering Adversarial Images using Input Transformations ICLR 2018