{"total":86,"rows":[{"id":"2309.00614","title":"Baseline Defenses for Adversarial Attacks Against Aligned Language Models","created":"2023-09-01","cited_by_count":651,"area":"alignment"},{"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":"2103.06504","title":"Adversarial Laser Beam: Effective Physical-World Attack to DNNs in a Blink","created":"2021-03-11","cited_by_count":75,"area":null},{"id":"2305.10665","title":"Content-based Unrestricted Adversarial Attack","created":"2023-05-18","cited_by_count":73,"area":null},{"id":"2305.16494","title":"Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability","created":"2023-05-25","cited_by_count":66,"area":null},{"id":"2108.09034","title":"AdvDrop: Adversarial Attack to DNNs by Dropping Information","created":"2021-08-20","cited_by_count":56,"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":"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":"2206.04310","title":"GSmooth: Certified Robustness against Semantic Transformations via Generalized Randomized Smoothing","created":"2022-06-09","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":"2109.10696","title":"CC-Cert: A Probabilistic Approach to Certify General Robustness of Neural Networks","created":"2021-09-22","cited_by_count":19,"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":"2107.01396","title":"Demiguise Attack: Crafting Invisible Semantic Adversarial Perturbations with Perceptual Similarity","created":"2021-07-03","cited_by_count":18,"area":null},{"id":"2203.08725","title":"Attacking deep networks with surrogate-based adversarial black-box methods is easy","created":"2022-03-16","cited_by_count":18,"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":"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":"2201.01102","title":"Towards Transferable Unrestricted Adversarial Examples with Minimum Changes","created":"2022-01-04","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":"2106.00576","title":"Exposing Previously Undetectable Faults in Deep Neural Networks","created":"2021-06-01","cited_by_count":11,"area":null},{"id":"2202.07201","title":"Holistic Adversarial Robustness of Deep Learning Models","created":"2022-02-15","cited_by_count":11,"area":null},{"id":"2206.01034","title":"Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs","created":"2022-06-02","cited_by_count":11,"area":null},{"id":"2209.02430","title":"Adversarial Color Film: Effective Physical-World Attack to DNNs","created":"2022-09-02","cited_by_count":11,"area":null},{"id":"2202.07184","title":"On the Origins of the Block Structure Phenomenon in Neural Network Representations","created":"2022-02-15","cited_by_count":10,"area":null},{"id":"2305.08840","title":"Attacking Perceptual Similarity Metrics","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2203.00849","title":"Adversarially Robust Learning with Tolerance","created":"2022-03-02","cited_by_count":9,"area":null},{"id":"2205.08589","title":"Hierarchical Distribution-Aware Testing of Deep Learning","created":"2022-05-17","cited_by_count":8,"area":null},{"id":"2502.00718","title":"\"I am bad\": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models","created":"2025-02-02","cited_by_count":8,"area":"safety"},{"id":"2108.02502","title":"Imperceptible Adversarial Examples by Spatial Chroma-Shift","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2210.00973","title":"NCVX: A General-Purpose Optimization Solver for Constrained Machine and Deep Learning","created":"2022-10-03","cited_by_count":7,"area":null},{"id":"2105.09685","title":"Simple Transparent Adversarial Examples","created":"2021-05-20","cited_by_count":6,"area":null},{"id":"2204.00853","title":"Adversarial Neon Beam: A Light-based Physical Attack to DNNs","created":"2022-04-02","cited_by_count":6,"area":null},{"id":"2210.08870","title":"Differential Evolution based Dual Adversarial Camouflage: Fooling Human Eyes and Object Detectors","created":"2022-10-17","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":"2506.23908","title":"Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence","created":"2025-06-30","cited_by_count":6,"area":"lr"},{"id":"2103.07640","title":"Generating Unrestricted Adversarial Examples via Three Parameters","created":"2021-03-13","cited_by_count":5,"area":null},{"id":"2207.07797","title":"CARBEN: Composite Adversarial Robustness Benchmark","created":"2022-07-16","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":"2206.12251","title":"Adversarial Zoom Lens: A Novel Physical-World Attack to DNNs","created":"2022-06-23","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":"2307.09375","title":"CertPri: Certifiable Prioritization for Deep Neural Networks via Movement Cost in Feature Space","created":"2023-07-18","cited_by_count":4,"area":null},{"id":"2309.09480","title":"Stealthy Physical Masked Face Recognition Attack via Adversarial Style Optimization","created":"2023-09-18","cited_by_count":4,"area":null},{"id":"2402.03095","title":"Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semantics","created":"2024-02-05","cited_by_count":4,"area":null},{"id":"2410.08620","title":"Natural Language Induced Adversarial Images","created":"2024-10-11","cited_by_count":4,"area":null},{"id":"2106.16198","title":"In-distribution adversarial attacks on object recognition models using gradient-free search","created":"2021-06-30","cited_by_count":3,"area":null},{"id":"2205.15944","title":"Hide and Seek: on the Stealthiness of Attacks against Deep Learning Systems","created":"2022-05-31","cited_by_count":3,"area":null},{"id":"2210.00621","title":"Optimization for Robustness Evaluation beyond $\\ell_p$ Metrics","created":"2022-10-02","cited_by_count":3,"area":null},{"id":"2211.11880","title":"Addressing Mistake Severity in Neural Networks with Semantic Knowledge","created":"2022-11-21","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":"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":"2206.10858","title":"Robust Universal Adversarial Perturbations","created":"2022-06-22","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":"2309.13150","title":"Pixel-wise Smoothing for Certified Robustness against Camera Motion Perturbations","created":"2023-09-22","cited_by_count":2,"area":null},{"id":"2403.02329","title":"COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attacks","created":"2024-03-04","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":"2209.02408","title":"Robustness and invariance properties of image classifiers","created":"2022-08-30","cited_by_count":1,"area":null},{"id":"2209.09652","title":"Adversarial Color Projection: A Projector-based Physical Attack to DNNs","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2209.11739","title":"Adversarial Catoptric Light: An Effective, Stealthy and Robust Physical-World Attack to DNNs","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2404.00185","title":"On Inherent Adversarial Robustness of Active Vision Systems","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2505.24227","title":"Light as Deception: GPT-driven Natural Relighting Against Vision-Language Pre-training Models","created":"2025-05-30","cited_by_count":1,"area":"mllm"},{"id":"2507.07776","title":"SCOOTER: A Human Evaluation Framework for Unrestricted Adversarial Examples","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2509.25927","title":"The Impact of Scaling Training Data on Adversarial Robustness","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2102.00449","title":"Towards Imperceptible Query-limited Adversarial Attacks with Perceptual Feature Fidelity Loss","created":"2021-01-31","cited_by_count":0,"area":null},{"id":"2109.10499","title":"Joint Optical Neuroimaging Denoising with Semantic Tasks","created":"2021-09-22","cited_by_count":0,"area":null},{"id":"2301.01343","title":"Explainability and Robustness of Deep Visual Classification Models","created":"2023-01-03","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":"2309.16710","title":"General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothing","created":"2023-08-17","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":"2312.06163","title":"Adversarial Camera Patch: An Effective and Robust Physical-World Attack on Object Detectors","created":"2023-12-11","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":"2504.08782","title":"Embedding Hidden Adversarial Capabilities in Pre-Trained Diffusion Models","created":"2025-04-05","cited_by_count":0,"area":"diffusion"},{"id":"2505.16166","title":"TRAIL: Transferable Robust Adversarial Images via Latent diffusion","created":"2025-05-22","cited_by_count":0,"area":"diffusion"},{"id":"2511.13535","title":"Accuracy is Not Enough: Poisoning Interpretability in Federated Learning via Color Skew","created":"2025-11-17","cited_by_count":0,"area":null},{"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":"2606.28416","title":"AEGIS: A Semantic GAN and Evidential Learning Frameworkfor Robust Adversarial Detection in Vision Sensors","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.27292","title":"VETO: Towards Protecting Images From Frontier AI Editing","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.30478","title":"The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}