{"total":56,"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":"2105.11417","title":"Skew Orthogonal Convolutions","created":"2021-05-24","cited_by_count":67,"area":null},{"id":"2110.12690","title":"A Dynamical System Perspective for Lipschitz Neural Networks","created":"2021-10-25","cited_by_count":60,"area":null},{"id":"2103.03046","title":"PointGuard: Provably Robust 3D Point Cloud Classification","created":"2021-03-04","cited_by_count":49,"area":null},{"id":"2108.04062","title":"Improved deterministic l2 robustness on CIFAR-10 and CIFAR-100","created":"2021-08-05","cited_by_count":47,"area":null},{"id":"2107.14569","title":"Can You Hear It? Backdoor Attacks via Ultrasonic Triggers","created":"2021-07-30","cited_by_count":44,"area":null},{"id":"2207.00425","title":"Transferable Graph Backdoor Attack","created":"2022-06-21","cited_by_count":19,"area":null},{"id":"2102.04661","title":"Security and Privacy for Artificial Intelligence: Opportunities and Challenges","created":"2021-02-09","cited_by_count":16,"area":null},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","cited_by_count":14,"area":null},{"id":"2112.03000","title":"Sequential Randomized Smoothing for Adversarially Robust Speech Recognition","created":"2021-11-05","cited_by_count":13,"area":null},{"id":"2112.05282","title":"RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit","created":"2021-12-10","cited_by_count":11,"area":null},{"id":"2111.14564","title":"MedRDF: A Robust and Retrain-Less Diagnostic Framework for Medical Pretrained Models Against Adversarial Attack","created":"2021-11-29","cited_by_count":9,"area":null},{"id":"2203.00849","title":"Adversarially Robust Learning with Tolerance","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2210.01111","title":"MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples","created":"2022-10-03","cited_by_count":9,"area":null},{"id":"2211.08453","title":"Improved techniques for deterministic l2 robustness","created":"2022-11-15","cited_by_count":9,"area":null},{"id":"2301.11544","title":"Targeted Attacks on Timeseries Forecasting","created":"2023-01-27","cited_by_count":8,"area":null},{"id":"2401.08903","title":"Rethinking Impersonation and Dodging Attacks on Face Recognition Systems","created":"2024-01-17","cited_by_count":8,"area":null},{"id":"2112.07921","title":"Temporal Shuffling for Defending Deep Action Recognition Models against Adversarial Attacks","created":"2021-12-15","cited_by_count":7,"area":null},{"id":"2106.14432","title":"Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations","created":"2021-06-28","cited_by_count":6,"area":null},{"id":"2107.02045","title":"Understanding the Security of Deepfake Detection","created":"2021-07-05","cited_by_count":6,"area":null},{"id":"2110.15444","title":"10 Security and Privacy Problems in Large Foundation Models","created":"2021-10-28","cited_by_count":6,"area":null},{"id":"2303.01959","title":"PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees","created":"2023-03-03","cited_by_count":6,"area":null},{"id":"2403.13778","title":"Certified Human Trajectory Prediction","created":"2024-03-20","cited_by_count":6,"area":null},{"id":"2407.09050","title":"Refusing Safe Prompts for Multi-modal Large Language Models","created":"2024-07-12","cited_by_count":6,"area":"mllm"},{"id":"2207.06035","title":"Perturbation Inactivation Based Adversarial Defense for Face Recognition","created":"2022-07-13","cited_by_count":5,"area":null},{"id":"2411.03279","title":"Oblivious Defense in ML Models: Backdoor Removal without Detection","created":"2024-11-05","cited_by_count":5,"area":null},{"id":"2212.03334","title":"Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning","created":"2022-12-06","cited_by_count":4,"area":"safety"},{"id":"2210.13463","title":"Adversarial Pretraining of Self-Supervised Deep Networks: Past, Present and Future","created":"2022-10-23","cited_by_count":3,"area":null},{"id":"2301.02905","title":"REaaS: Enabling Adversarially Robust Downstream Classifiers via Robust Encoder as a Service","created":"2023-01-07","cited_by_count":3,"area":null},{"id":"2306.01655","title":"Poisoning Network Flow Classifiers","created":"2023-06-02","cited_by_count":3,"area":null},{"id":"2105.00495","title":"BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability","created":"2021-05-02","cited_by_count":2,"area":null},{"id":"2109.12459","title":"Two Souls in an Adversarial Image: Towards Universal Adversarial Example Detection using Multi-view Inconsistency","created":"2021-09-25","cited_by_count":2,"area":null},{"id":"2210.14260","title":"Universal Evasion Attacks on Summarization Scoring","created":"2022-10-25","cited_by_count":2,"area":null},{"id":"2306.05494","title":"Evasion Adversarial Attacks Remain Impractical Against ML-based Network Intrusion Detection Systems, Especially Dynamic Ones","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2406.18144","title":"Artificial Immune System of Secure Face Recognition Against Adversarial Attacks","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2102.05096","title":"Towards Bridging the gap between Empirical and Certified Robustness against Adversarial Examples","created":"2021-02-09","cited_by_count":1,"area":null},{"id":"2107.09804","title":"Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attacks","created":"2021-07-20","cited_by_count":1,"area":null},{"id":"2207.05127","title":"RUSH: Robust Contrastive Learning via Randomized Smoothing","created":"2022-07-11","cited_by_count":1,"area":null},{"id":"2209.08412","title":"Characterizing Internal Evasion Attacks in Federated Learning","created":"2022-09-17","cited_by_count":1,"area":null},{"id":"2210.08929","title":"DE-CROP: Data-efficient Certified Robustness for Pretrained Classifiers","created":"2022-10-17","cited_by_count":1,"area":null},{"id":"2310.11594","title":"Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning","created":"2023-10-17","cited_by_count":1,"area":null},{"id":"2404.18825","title":"Harmonic Machine Learning Models are Robust","created":"2024-04-29","cited_by_count":1,"area":null},{"id":"2405.19956","title":"HOLMES: to Detect Adversarial Examples with Multiple Detectors","created":"2024-05-30","cited_by_count":1,"area":null},{"id":"2412.02535","title":"Defending Against Diverse Attacks in Federated Learning Through Consensus-Based Bi-Level Optimization","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2604.09024","title":"Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection","created":"2026-04-10","cited_by_count":1,"area":"mllm"},{"id":"2102.02923","title":"PredCoin: Defense against Query-based Hard-label Attack","created":"2021-02-04","cited_by_count":0,"area":null},{"id":"2106.05825","title":"HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2208.00498","title":"DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning","created":"2022-07-31","cited_by_count":0,"area":null},{"id":"2208.14488","title":"Constraining Representations Yields Models That Know What They Don't Know","created":"2022-08-30","cited_by_count":0,"area":null},{"id":"2305.19265","title":"Probabilistic computation and uncertainty quantification with emerging covariance","created":"2023-05-30","cited_by_count":0,"area":null},{"id":"2309.17278","title":"Toward Robust Recommendation via Real-time Vicinal Defense","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2401.11723","title":"Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them","created":"2024-01-22","cited_by_count":0,"area":null},{"id":"2503.06188","title":"Attackers Can Do Better: Over- and Understated Factors of Model Stealing Attacks","created":"2025-03-08","cited_by_count":0,"area":null},{"id":"2503.10661","title":"CeTAD: Towards Certified Toxicity-Aware Distance in Vision Language Models","created":"2025-03-08","cited_by_count":0,"area":"mllm"},{"id":"2504.10850","title":"How to Enhance Downstream Adversarial Robustness (almost) without Touching the Pre-Trained Foundation Model?","created":"2025-04-15","cited_by_count":0,"area":null},{"id":"2603.14768","title":"Understanding the geometry of deep learning with decision boundary volume","created":"2026-03-16","cited_by_count":0,"area":null}],"next_cursor":null}