{"total":84,"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":"2305.08192","title":"Diffusion Models for Imperceptible and Transferable Adversarial Attack","created":"2023-05-14","cited_by_count":94,"area":"diffusion"},{"id":"2305.10665","title":"Content-based Unrestricted Adversarial Attack","created":"2023-05-18","cited_by_count":73,"area":null},{"id":"2207.04892","title":"Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentation","created":"2022-07-11","cited_by_count":70,"area":null},{"id":"2111.09277","title":"SmoothMix: Training Confidence-calibrated Smoothed Classifiers for Certified Robustness","created":"2021-11-17","cited_by_count":49,"area":null},{"id":"2101.06784","title":"Exploring Adversarial Robustness of Multi-Sensor Perception Systems in Self Driving","created":"2021-01-17","cited_by_count":45,"area":null},{"id":"2108.06247","title":"Optical Adversarial Attack","created":"2021-08-13","cited_by_count":43,"area":null},{"id":"2306.10008","title":"CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search","created":"2023-06-16","cited_by_count":43,"area":null},{"id":"2107.10873","title":"On the Certified Robustness for Ensemble Models and Beyond","created":"2021-07-22","cited_by_count":40,"area":null},{"id":"2210.02041","title":"Natural Color Fool: Towards Boosting Black-box Unrestricted Attacks","created":"2022-10-05","cited_by_count":38,"area":null},{"id":"2111.09999","title":"TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems","created":"2021-11-19","cited_by_count":36,"area":null},{"id":"2104.13673","title":"AdvHaze: Adversarial Haze Attack","created":"2021-04-28","cited_by_count":31,"area":null},{"id":"2105.05558","title":"AVA: Adversarial Vignetting Attack against Visual Recognition","created":"2021-05-12","cited_by_count":29,"area":null},{"id":"2110.03605","title":"Robust Feature-Level Adversaries are Interpretability Tools","created":"2021-10-07","cited_by_count":27,"area":null},{"id":"2408.01428","title":"Transferable Adversarial Facial Images for Privacy Protection","created":"2024-07-18","cited_by_count":27,"area":null},{"id":"2202.04235","title":"Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations","created":"2022-02-09","cited_by_count":26,"area":null},{"id":"2106.06235","title":"Knowledge Enhanced Machine Learning Pipeline against Diverse Adversarial Attacks","created":"2021-06-11","cited_by_count":24,"area":null},{"id":"2110.09903","title":"Unrestricted Adversarial Attacks on ImageNet Competition","created":"2021-10-17","cited_by_count":23,"area":null},{"id":"2109.02765","title":"Robustness and Generalization via Generative Adversarial Training","created":"2021-09-06","cited_by_count":20,"area":null},{"id":"2203.16000","title":"StyleFool: Fooling Video Classification Systems via Style Transfer","created":"2022-03-30","cited_by_count":20,"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":"2208.11613","title":"Unrestricted Black-box Adversarial Attack Using GAN with Limited Queries","created":"2022-08-24","cited_by_count":18,"area":null},{"id":"2108.07920","title":"Adversarial Relighting Against Face Recognition","created":"2021-08-18","cited_by_count":16,"area":null},{"id":"2311.15551","title":"Instruct2Attack: Language-Guided Semantic Adversarial Attacks","created":"2023-11-27","cited_by_count":16,"area":null},{"id":"2312.12720","title":"AdvST: Revisiting Data Augmentations for Single Domain Generalization","created":"2023-12-20","cited_by_count":16,"area":null},{"id":"2211.09565","title":"Towards Good Practices in Evaluating Transfer Adversarial Attacks","created":"2022-11-17","cited_by_count":15,"area":null},{"id":"2201.01102","title":"Towards Transferable Unrestricted Adversarial Examples with Minimum Changes","created":"2022-01-04","cited_by_count":13,"area":null},{"id":"2209.09502","title":"GAMA: Generative Adversarial Multi-Object Scene Attacks","created":"2022-09-20","cited_by_count":13,"area":null},{"id":"2309.07398","title":"Semantic Adversarial Attacks via Diffusion Models","created":"2023-09-14","cited_by_count":12,"area":"diffusion"},{"id":"2305.08840","title":"Attacking Perceptual Similarity Metrics","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2402.19322","title":"Verification of Neural Networks' Global Robustness","created":"2024-02-29","cited_by_count":10,"area":null},{"id":"2408.12387","title":"Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priors","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2108.02502","title":"Imperceptible Adversarial Examples by Spatial Chroma-Shift","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2201.10972","title":"How Robust are Discriminatively Trained Zero-Shot Learning Models?","created":"2022-01-26","cited_by_count":6,"area":null},{"id":"2301.09069","title":"Provable Unrestricted Adversarial Training without Compromise with Generalizability","created":"2023-01-22","cited_by_count":6,"area":null},{"id":"2505.20934","title":"NatADiff: Adversarial Boundary Guidance for Natural Adversarial Diffusion","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2102.11586","title":"Adversarial Examples Detection beyond Image Space","created":"2021-02-23","cited_by_count":5,"area":null},{"id":"2103.07640","title":"Generating Unrestricted Adversarial Examples via Three Parameters","created":"2021-03-13","cited_by_count":5,"area":null},{"id":"2208.06222","title":"Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generator","created":"2022-08-12","cited_by_count":5,"area":null},{"id":"2408.01541","title":"Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics","created":"2024-08-02","cited_by_count":5,"area":null},{"id":"2408.08989","title":"Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models","created":"2024-08-16","cited_by_count":5,"area":null},{"id":"2504.21646","title":"Diffusion-based Adversarial Identity Manipulation for Facial Privacy Protection","created":"2025-04-30","cited_by_count":5,"area":null},{"id":"2103.00250","title":"Effective Universal Unrestricted Adversarial Attacks using a MOE Approach","created":"2021-02-27","cited_by_count":4,"area":null},{"id":"2104.11691","title":"Patch Shortcuts: Interpretable Proxy Models Efficiently Find Black-Box Vulnerabilities","created":"2021-04-22","cited_by_count":4,"area":null},{"id":"2111.12971","title":"Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network","created":"2021-11-25","cited_by_count":4,"area":null},{"id":"2209.05446","title":"Boosting Robustness Verification of Semantic Feature Neighborhoods","created":"2022-09-12","cited_by_count":4,"area":null},{"id":"2306.00353","title":"Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective","created":"2023-06-01","cited_by_count":4,"area":null},{"id":"2104.08422","title":"Fashion-Guided Adversarial Attack on Person Segmentation","created":"2021-04-17","cited_by_count":3,"area":null},{"id":"2312.13628","title":"Where and How to Attack? A Causality-Inspired Recipe for Generating Counterfactual Adversarial Examples","created":"2023-12-21","cited_by_count":3,"area":null},{"id":"2408.05479","title":"ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack","created":"2024-08-10","cited_by_count":3,"area":"diffusion"},{"id":"2410.02240","title":"SCA: Improve Semantic Consistent in Unrestricted Adversarial Attacks via DDPM Inversion","created":"2024-10-03","cited_by_count":3,"area":"diffusion"},{"id":"2411.11795","title":"Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods","created":"2024-11-18","cited_by_count":3,"area":null},{"id":"2506.01511","title":"Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment","created":"2025-06-02","cited_by_count":3,"area":"diffusion"},{"id":"2506.10685","title":"Defensive Adversarial CAPTCHA: A Semantics-Driven Framework for Natural Adversarial Example Generation","created":"2025-06-12","cited_by_count":3,"area":null},{"id":"2507.06078","title":"ScoreAdv: Score-based Targeted Generation of Natural Adversarial Examples via Diffusion Models","created":"2025-07-08","cited_by_count":3,"area":"diffusion"},{"id":"2107.09502","title":"Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features","created":"2021-07-19","cited_by_count":2,"area":null},{"id":"2206.10858","title":"Robust Universal Adversarial Perturbations","created":"2022-06-22","cited_by_count":2,"area":null},{"id":"2206.14020","title":"Rethinking Adversarial Examples for Location Privacy Protection","created":"2022-06-28","cited_by_count":2,"area":null},{"id":"2211.09782","title":"Assessing Neural Network Robustness via Adversarial Pivotal Tuning","created":"2022-11-17","cited_by_count":2,"area":null},{"id":"2305.07308","title":"Efficient Search of Comprehensively Robust Neural Architectures via Multi-fidelity Evaluation","created":"2023-05-12","cited_by_count":2,"area":null},{"id":"2309.11667","title":"Understanding Pose and Appearance Disentanglement in 3D Human Pose Estimation","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2407.08514","title":"Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems","created":"2024-07-11","cited_by_count":2,"area":null},{"id":"2507.02965","title":"Concept-based Adversarial Attack: a Probabilistic Perspective","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2102.13170","title":"Understanding Robustness in Teacher-Student Setting: A New Perspective","created":"2021-02-25","cited_by_count":1,"area":"distill"},{"id":"2106.09222","title":"Localized Uncertainty Attacks","created":"2021-06-17","cited_by_count":1,"area":null},{"id":"2202.06242","title":"Beyond NaN: Resiliency of Optimization Layers in The Face of Infeasibility","created":"2022-02-13","cited_by_count":1,"area":null},{"id":"2306.07178","title":"Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions","created":"2023-06-12","cited_by_count":1,"area":null},{"id":"2310.00503","title":"Black-box Attacks on Image Activity Prediction and its Natural Language Explanations","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2504.11034","title":"Defending Against Frequency-Based Attacks with Diffusion Models","created":"2025-04-15","cited_by_count":1,"area":"diffusion"},{"id":"2507.07776","title":"SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2105.14710","title":"Robustifying $\\ell_\\infty$ Adversarial Training to the Union of Perturbation Models","created":"2021-05-31","cited_by_count":0,"area":null},{"id":"2202.04978","title":"Towards Assessing and Characterizing the Semantic Robustness of Face Recognition","created":"2022-02-10","cited_by_count":0,"area":null},{"id":"2209.02406","title":"Unrestricted Adversarial Samples Based on Non-semantic Feature Clusters Substitution","created":"2022-08-31","cited_by_count":0,"area":null},{"id":"2209.15084","title":"Automatic satellite building construction monitoring","created":"2022-09-29","cited_by_count":0,"area":null},{"id":"2303.03400","title":"Testing the Channels of Convolutional Neural Networks","created":"2023-03-06","cited_by_count":0,"area":null},{"id":"2307.06548","title":"Multi-objective Evolutionary Search of Variable-length Composite Semantic Perturbations","created":"2023-07-13","cited_by_count":0,"area":null},{"id":"2311.16478","title":"RetouchUAA: Unconstrained Adversarial Attack via Image Retouching","created":"2023-11-27","cited_by_count":0,"area":null},{"id":"2405.07969","title":"Investigating the Semantic Robustness of CLIP-based Zero-Shot Anomaly Segmentation","created":"2024-05-13","cited_by_count":0,"area":null},{"id":"2408.00193","title":"Resilience and Security of Deep Neural Networks Against Intentional and Unintentional Perturbations: Survey and Research Challenges","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2412.01725","title":"Attacks on multimodal models","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2505.16166","title":"TRAIL: Transferable Robust Adversarial Images via Latent diffusion","created":"2025-05-22","cited_by_count":0,"area":"diffusion"},{"id":"2606.05101","title":"FoeGlass: Simple In-Context Learning Is Enough for Red Teaming Audio Deepfake Detectors","created":"2026-06-03","cited_by_count":0,"area":"safety"},{"id":"2606.17540","title":"TaFD: Threat-Aware Frequency Decoupling for Adversarial Robustness against Heterogeneous Attacks","created":"2026-06-16","cited_by_count":0,"area":null},{"id":"2610.11938","title":"Does Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive Encoders","created":"2026-10-08","cited_by_count":0,"area":"mllm"}],"next_cursor":null}