{"total":70,"rows":[{"id":"2108.00401","title":"Advances in adversarial attacks and defenses in computer vision: A survey","created":"2021-08-01","cited_by_count":127,"area":null},{"id":"2102.12781","title":"Do Input Gradients Highlight Discriminative Features?","created":"2021-02-25","cited_by_count":52,"area":null},{"id":"2310.17626","title":"A Survey on Transferability of Adversarial Examples across Deep Neural Networks","created":"2023-10-26","cited_by_count":44,"area":null},{"id":"2106.10151","title":"The Dimpled Manifold Model of Adversarial Examples in Machine Learning","created":"2021-06-18","cited_by_count":41,"area":null},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37,"area":"safety"},{"id":"2111.09961","title":"A Review of Adversarial Attack and Defense for Classification Methods","created":"2021-11-18","cited_by_count":29,"area":null},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2106.02749","title":"Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics","created":"2021-06-04","cited_by_count":19,"area":null},{"id":"2202.02842","title":"Evaluating natural language processing models with generalization metrics that do not need access to any training or testing data","created":"2022-02-06","cited_by_count":19,"area":null},{"id":"2211.02878","title":"Textual Manifold-based Defense Against Natural Language Adversarial Examples","created":"2022-11-05","cited_by_count":19,"area":null},{"id":"2102.06479","title":"Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective","created":"2021-02-12","cited_by_count":18,"area":null},{"id":"2212.05680","title":"REAP: A Large-Scale Realistic Adversarial Patch Benchmark","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2106.06418","title":"Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scales","created":"2021-06-11","cited_by_count":17,"area":null},{"id":"2310.18936","title":"Adversarial Examples Are Not Real Features","created":"2023-10-29","cited_by_count":16,"area":null},{"id":"2209.04779","title":"Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense","created":"2022-09-11","cited_by_count":14,"area":null},{"id":"2111.05468","title":"Sparse Adversarial Video Attacks with Spatial Transformations","created":"2021-11-10","cited_by_count":11,"area":null},{"id":"2212.12641","title":"Out-of-Distribution Detection with Reconstruction Error and Typicality-based Penalty","created":"2022-12-24","cited_by_count":11,"area":null},{"id":"2309.01866","title":"Efficient Query-Based Attack against ML-Based Android Malware Detection under Zero Knowledge Setting","created":"2023-09-05","cited_by_count":10,"area":null},{"id":"2405.20355","title":"Enhancing Adversarial Robustness in SNNs with Sparse Gradients","created":"2024-05-30","cited_by_count":10,"area":null},{"id":"2303.09767","title":"It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness","created":"2023-03-17","cited_by_count":9,"area":null},{"id":"2303.00783","title":"Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces","created":"2023-03-01","cited_by_count":8,"area":null},{"id":"2310.13291","title":"Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2402.05674","title":"A High Dimensional Statistical Model for Adversarial Training: Geometry and Trade-Offs","created":"2024-02-08","cited_by_count":7,"area":null},{"id":"2108.07958","title":"Semantic Perturbations with Normalizing Flows for Improved Generalization","created":"2021-08-18","cited_by_count":6,"area":null},{"id":"2301.12896","title":"Identifying Adversarially Attackable and Robust Samples","created":"2023-01-30","cited_by_count":5,"area":null},{"id":"2304.08767","title":"Masked Language Model Based Textual Adversarial Example Detection","created":"2023-04-18","cited_by_count":5,"area":null},{"id":"2203.13277","title":"A Manifold View of Adversarial Risk","created":"2022-03-24","cited_by_count":4,"area":null},{"id":"2301.13869","title":"Reverse engineering adversarial attacks with fingerprints from adversarial examples","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2309.03665","title":"How adversarial attacks can disrupt seemingly stable accurate classifiers","created":"2023-09-07","cited_by_count":4,"area":null},{"id":"2410.16073","title":"On the Geometry of Regularization in Adversarial Training: High-Dimensional Asymptotics and Generalization Bounds","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2504.08798","title":"Exploring Gradient-Guided Masked Language Model to Detect Textual Adversarial Attacks","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2112.04720","title":"Amicable Aid: Perturbing Images to Improve Classification Performance","created":"2021-12-09","cited_by_count":3,"area":null},{"id":"2304.14601","title":"Improve Video Representation with Temporal Adversarial Augmentation","created":"2023-04-28","cited_by_count":3,"area":null},{"id":"2404.10789","title":"PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysis","created":"2024-04-12","cited_by_count":3,"area":null},{"id":"2105.08620","title":"Adversarial Examples Detection with Bayesian Neural Network","created":"2021-05-18","cited_by_count":2,"area":null},{"id":"2204.10046","title":"Testing robustness of predictions of trained classifiers against naturally occurring perturbations","created":"2022-04-21","cited_by_count":2,"area":null},{"id":"2302.10896","title":"IB-RAR: Information Bottleneck as Regularizer for Adversarial Robustness","created":"2023-02-09","cited_by_count":2,"area":null},{"id":"2405.17130","title":"Explaining the role of Intrinsic Dimensionality in Adversarial Training","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2107.10599","title":"Towards Explaining Adversarial Examples Phenomenon in Artificial Neural Networks","created":"2021-07-22","cited_by_count":1,"area":null},{"id":"2112.04033","title":"Image classifiers can not be made robust to small perturbations","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2205.15357","title":"Searching for the Essence of Adversarial Perturbations","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2206.04316","title":"Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks","created":"2022-06-09","cited_by_count":1,"area":null},{"id":"2302.03750","title":"Linking convolutional kernel size to generalization bias in face analysis CNNs","created":"2023-02-07","cited_by_count":1,"area":null},{"id":"2306.04252","title":"Adversarial Sample Detection Through Neural Network Transport Dynamics","created":"2023-06-07","cited_by_count":1,"area":null},{"id":"2402.02154","title":"Evaluating the Robustness of Off-Road Autonomous Driving Segmentation against Adversarial Attacks: A Dataset-Centric analysis","created":"2024-02-03","cited_by_count":1,"area":null},{"id":"2403.16176","title":"Subspace Defense: Discarding Adversarial Perturbations by Learning a Subspace for Clean Signals","created":"2024-03-24","cited_by_count":1,"area":null},{"id":"2406.16200","title":"Feature compression is the root cause of adversarial fragility in neural network classifiers","created":"2024-06-23","cited_by_count":1,"area":null},{"id":"2407.02240","title":"MALT Powers Up Adversarial Attacks","created":"2024-07-02","cited_by_count":1,"area":null},{"id":"2408.14728","title":"Improving Clean Accuracy via a Tangent-Space Perspective on Adversarial Training","created":"2024-08-27","cited_by_count":1,"area":null},{"id":"2503.06361","title":"Adversarial Robustness of Discriminative Self-Supervised Learning in Vision","created":"2025-03-08","cited_by_count":1,"area":null},{"id":"2505.24592","title":"A Flat Minima Perspective on Understanding Augmentations and Model Robustness","created":"2025-05-30","cited_by_count":1,"area":null},{"id":"2511.15107","title":"Effective Code Membership Inference for Code Completion Models via Adversarial Prompts","created":"2025-11-19","cited_by_count":1,"area":"safety"},{"id":"2603.03507","title":"Solving adversarial examples requires solving exponential misalignment","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2103.03325","title":"Hard-label Manifolds: Unexpected Advantages of Query Efficiency for Finding On-manifold Adversarial Examples","created":"2021-03-04","cited_by_count":0,"area":null},{"id":"2106.09872","title":"Analyzing Adversarial Robustness of Deep Neural Networks in Pixel Space: a Semantic Perspective","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2109.12756","title":"A novel network training approach for open set image recognition","created":"2021-09-27","cited_by_count":0,"area":null},{"id":"2110.12357","title":"Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples","created":"2021-10-24","cited_by_count":0,"area":null},{"id":"2203.02121","title":"Adversarial Patterns: Building Robust Android Malware Classifiers","created":"2022-03-04","cited_by_count":0,"area":null},{"id":"2205.13502","title":"An Analytic Framework for Robust Training of Artificial Neural Networks","created":"2022-05-26","cited_by_count":0,"area":null},{"id":"2309.10916","title":"What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples","created":"2023-09-19","cited_by_count":0,"area":null},{"id":"2309.15669","title":"On the Computational Entanglement of Distant Features in Adversarial Machine Learning","created":"2023-09-27","cited_by_count":0,"area":null},{"id":"2309.16878","title":"Investigating Human-Identifiable Features Hidden in Adversarial Perturbations","created":"2023-09-28","cited_by_count":0,"area":null},{"id":"2309.17048","title":"On Continuity of Robust and Accurate Classifiers","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2310.14045","title":"Training Image Derivatives: Increased Accuracy and Universal Robustness","created":"2023-10-21","cited_by_count":0,"area":null},{"id":"2410.13193","title":"Golyadkin's Torment: Doppelg\\\"angers and Adversarial Vulnerability","created":"2024-10-17","cited_by_count":0,"area":null},{"id":"2601.00577","title":"Adversarial Samples Are Not Created Equal","created":"2026-01-02","cited_by_count":0,"area":null},{"id":"2602.07009","title":"Multi-Scale Temporal Homeostasis Enables Efficient and Robust Neural Networks","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.06311","title":"Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2606.04209","title":"A Geometric View of Counterfactual Behavior: Interaction of Boundary Proximity and Local Support","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.20581","title":"Geometric Configurations of Perturbed Jailbreak Prompts","created":"2026-07-22","cited_by_count":0,"area":"safety"}],"next_cursor":null}