{"total":51,"rows":[{"id":"2109.13916","title":"Unsolved Problems in ML Safety","created":"2021-09-28","cited_by_count":292,"area":null},{"id":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"area":null},{"id":"2106.05036","title":"Towards Defending against Adversarial Examples via Attack-Invariant Features","created":"2021-06-09","cited_by_count":25,"area":null},{"id":"2210.15291","title":"Isometric 3D Adversarial Examples in the Physical World","created":"2022-10-27","cited_by_count":25,"area":null},{"id":"2207.05164","title":"Machine Learning Security in Industry: A Quantitative Survey","created":"2022-07-11","cited_by_count":21,"area":null},{"id":"2310.00633","title":"A Survey of Robustness and Safety of 2D and 3D Deep Learning Models Against Adversarial Attacks","created":"2023-10-01","cited_by_count":19,"area":null},{"id":"2104.09197","title":"Removing Adversarial Noise in Class Activation Feature Space","created":"2021-04-19","cited_by_count":18,"area":null},{"id":"2311.09994","title":"Towards more Practical Threat Models in Artificial Intelligence Security","created":"2023-11-16","cited_by_count":17,"area":null},{"id":"2210.06077","title":"Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivity","created":"2022-10-12","cited_by_count":15,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2203.02006","title":"Why adversarial training can hurt robust accuracy","created":"2022-03-03","cited_by_count":14,"area":null},{"id":"2103.16910","title":"Trusted Artificial Intelligence: Towards Certification of Machine Learning Applications","created":"2021-03-31","cited_by_count":13,"area":null},{"id":"2306.02895","title":"Evading Black-box Classifiers Without Breaking Eggs","created":"2023-06-05","cited_by_count":13,"area":null},{"id":"2103.00676","title":"Token-Modification Adversarial Attacks for Natural Language Processing: A Survey","created":"2021-03-01","cited_by_count":12,"area":null},{"id":"2106.00576","title":"Exposing Previously Undetectable Faults in Deep Neural Networks","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2202.13216","title":"Adversarial robustness of sparse local Lipschitz predictors","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2102.05431","title":"Dompteur: Taming Audio Adversarial Examples","created":"2021-02-10","cited_by_count":10,"area":null},{"id":"2102.11731","title":"Rethinking Natural Adversarial Examples for Classification Models","created":"2021-02-23","cited_by_count":9,"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":"2404.00897","title":"Machine Learning Robustness: A Primer","created":"2024-04-01","cited_by_count":8,"area":null},{"id":"2104.00322","title":"Domain Invariant Adversarial Learning","created":"2021-04-01","cited_by_count":7,"area":null},{"id":"2111.04204","title":"Natural Adversarial Objects","created":"2021-11-07","cited_by_count":7,"area":null},{"id":"2310.17645","title":"PubDef: Defending Against Transfer Attacks From Public Models","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2402.01879","title":"$\\sigma$-zero: Gradient-based Optimization of $\\ell_0$-norm Adversarial Examples","created":"2024-02-02","cited_by_count":7,"area":null},{"id":"2103.01276","title":"A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness","created":"2021-03-01","cited_by_count":6,"area":null},{"id":"2106.07141","title":"Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attacks","created":"2021-06-14","cited_by_count":6,"area":null},{"id":"2303.13401","title":"Optimization and Optimizers for Adversarial Robustness","created":"2023-03-23","cited_by_count":6,"area":null},{"id":"2303.14173","title":"How many dimensions are required to find an adversarial example?","created":"2023-03-24","cited_by_count":5,"area":null},{"id":"2109.00678","title":"Regional Adversarial Training for Better Robust Generalization","created":"2021-09-02","cited_by_count":4,"area":null},{"id":"2206.12725","title":"Empirical Evaluation of Physical Adversarial Patch Attacks Against Overhead Object Detection Models","created":"2022-06-25","cited_by_count":4,"area":null},{"id":"2211.02646","title":"Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2302.04379","title":"Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples","created":"2023-02-09","cited_by_count":4,"area":null},{"id":"2506.13024","title":"Position: Certified Robustness Does Not (Yet) Imply Model Security","created":"2025-06-16","cited_by_count":4,"area":null},{"id":"2108.07602","title":"When Should You Defend Your Classifier -- A Game-theoretical Analysis of Countermeasures against Adversarial Examples","created":"2021-08-17","cited_by_count":3,"area":null},{"id":"2108.11762","title":"Disentangling What and Where for 3D Object-Centric Representations Through Active Inference","created":"2021-08-26","cited_by_count":3,"area":null},{"id":"2104.08382","title":"Lower Bounds on Cross-Entropy Loss in the Presence of Test-time Adversaries","created":"2021-04-16","cited_by_count":1,"area":null},{"id":"2108.02010","title":"On the Exploitability of Audio Machine Learning Pipelines to Surreptitious Adversarial Examples","created":"2021-08-03","cited_by_count":1,"area":null},{"id":"2310.09361","title":"Is Certifying $\\ell_p$ Robustness Still Worthwhile?","created":"2023-10-13","cited_by_count":1,"area":null},{"id":"2402.14937","title":"SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2504.12255","title":"Human Aligned Compression for Robust Models","created":"2025-04-16","cited_by_count":1,"area":null},{"id":"2506.00047","title":"Risks of AI-driven product development and strategies for their mitigation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.17874","title":"Improving Mixup Calibration with Wasserstein Distributionally Robust Optimization","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2102.07360","title":"Generating Structured Adversarial Attacks Using Frank-Wolfe Method","created":"2021-02-15","cited_by_count":0,"area":null},{"id":"2105.03726","title":"Mental Models of Adversarial Machine Learning","created":"2021-05-08","cited_by_count":0,"area":null},{"id":"2205.15763","title":"Exact Feature Collisions in Neural Networks","created":"2022-05-31","cited_by_count":0,"area":null},{"id":"2309.12463","title":"Impact of architecture on robustness and interpretability of multispectral deep neural networks","created":"2023-09-21","cited_by_count":0,"area":null},{"id":"2311.07928","title":"Towards Improving Robustness Against Common Corruptions in Object Detectors Using Adversarial Contrastive Learning","created":"2023-11-14","cited_by_count":0,"area":null},{"id":"2501.18098","title":"Disentangling Safe and Unsafe Corruptions via Anisotropy and Locality","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2510.01676","title":"Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks","created":"2025-10-02","cited_by_count":0,"area":null},{"id":"2601.14519","title":"How Worst-Case Are Adversarial Attacks? Linking Adversarial and Perturbation Robustness","created":"2026-01-20","cited_by_count":0,"area":null}],"next_cursor":null}