{"total":101,"rows":[{"id":"2405.15556","title":"Certifiably Robust RAG against Retrieval Corruption","created":"2024-05-24","cited_by_count":151,"area":"rag"},{"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":"2108.00352","title":"BadEncoder: Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning","created":"2021-08-01","cited_by_count":123,"area":"safety"},{"id":"2112.04532","title":"Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection","created":"2021-12-08","cited_by_count":67,"area":null},{"id":"2108.09135","title":"PatchCleanser: Certifiably Robust Defense against Adversarial Patches for Any Image Classifier","created":"2021-08-20","cited_by_count":65,"area":null},{"id":"2210.04871","title":"Certified Training: Small Boxes are All You Need","created":"2022-10-10","cited_by_count":52,"area":null},{"id":"2107.11630","title":"Detecting Adversarial Examples Is (Nearly) As Hard As Classifying Them","created":"2021-07-24","cited_by_count":48,"area":null},{"id":"2110.07719","title":"Certified Patch Robustness via Smoothed Vision Transformers","created":"2021-10-11","cited_by_count":45,"area":null},{"id":"2203.08519","title":"Towards Practical Certifiable Patch Defense with Vision Transformer","created":"2022-03-16","cited_by_count":44,"area":null},{"id":"2207.07972","title":"Certified Neural Network Watermarks with Randomized Smoothing","created":"2022-07-16","cited_by_count":41,"area":null},{"id":"2106.11420","title":"Policy Smoothing for Provably Robust Reinforcement Learning","created":"2021-06-21","cited_by_count":40,"area":null},{"id":"2103.10834","title":"Improved, Deterministic Smoothing for L_1 Certified Robustness","created":"2021-03-17","cited_by_count":39,"area":null},{"id":"2106.10189","title":"Adversarial Training Helps Transfer Learning via Better Representations","created":"2021-06-18","cited_by_count":36,"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":"2207.01795","title":"PatchZero: Defending against Adversarial Patch Attacks by Detecting and Zeroing the Patch","created":"2022-07-05","cited_by_count":30,"area":null},{"id":"2102.02956","title":"DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attacks","created":"2021-02-05","cited_by_count":29,"area":null},{"id":"2104.12609","title":"PatchGuard++: Efficient Provable Attack Detection against Adversarial Patches","created":"2021-04-26","cited_by_count":29,"area":null},{"id":"2109.09032","title":"JEM++: Improved Techniques for Training JEM","created":"2021-09-19","cited_by_count":28,"area":null},{"id":"2102.04154","title":"Efficient Certified Defenses Against Patch Attacks on Image Classifiers","created":"2021-02-08","cited_by_count":24,"area":null},{"id":"2202.01811","title":"ObjectSeeker: Certifiably Robust Object Detection against Patch Hiding Attacks via Patch-agnostic Masking","created":"2022-02-03","cited_by_count":22,"area":null},{"id":"2101.11453","title":"Meta Adversarial Training against Universal Patches","created":"2021-01-27","cited_by_count":19,"area":null},{"id":"2111.04266","title":"Generative Dynamic Patch Attack","created":"2021-11-08","cited_by_count":19,"area":null},{"id":"2102.09701","title":"Center Smoothing: Certified Robustness for Networks with Structured Outputs","created":"2021-02-19","cited_by_count":18,"area":null},{"id":"2206.08304","title":"Adversarial Patch Attacks and Defences in Vision-Based Tasks: A Survey","created":"2022-06-16","cited_by_count":17,"area":null},{"id":"2302.02300","title":"Run-Off Election: Improved Provable Defense against Data Poisoning Attacks","created":"2023-02-05","cited_by_count":17,"area":"safety"},{"id":"2110.15629","title":"Attacking Video Recognition Models with Bullet-Screen Comments","created":"2021-10-29","cited_by_count":16,"area":null},{"id":"2209.05980","title":"Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation","created":"2022-09-13","cited_by_count":16,"area":null},{"id":"2110.14120","title":"ScaleCert: Scalable Certified Defense against Adversarial Patches with Sparse Superficial Layers","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2209.07959","title":"Towards Bridging the Performance Gaps of Joint Energy-based Models","created":"2022-09-16","cited_by_count":15,"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":"2306.09124","title":"DIFFender: Diffusion-Based Adversarial Defense against Patch Attacks","created":"2023-06-15","cited_by_count":15,"area":"diffusion"},{"id":"2401.03582","title":"Invisible Reflections: Leveraging Infrared Laser Reflections to Target Traffic Sign Perception","created":"2024-01-07","cited_by_count":14,"area":null},{"id":"2108.05075","title":"Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks","created":"2021-08-11","cited_by_count":13,"area":null},{"id":"2111.10481","title":"PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing","created":"2021-11-19","cited_by_count":12,"area":null},{"id":"2211.01671","title":"Visual Adversarial Attacks and Defenses in the Physical World: A Survey","created":"2022-11-03","cited_by_count":11,"area":null},{"id":"2309.16096","title":"Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness","created":"2023-09-28","cited_by_count":11,"area":null},{"id":"2310.13076","title":"PatchCURE: Improving Certifiable Robustness, Model Utility, and Computation Efficiency of Adversarial Patch Defenses","created":"2023-10-19","cited_by_count":11,"area":null},{"id":"2109.00542","title":"Shared Certificates for Neural Network Verification","created":"2021-09-01","cited_by_count":10,"area":null},{"id":"2112.06323","title":"Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses","created":"2021-12-12","cited_by_count":10,"area":null},{"id":"2311.01473","title":"Adversarial Examples in the Physical World: A Survey","created":"2023-11-01","cited_by_count":10,"area":null},{"id":"2204.13004","title":"Defending Person Detection Against Adversarial Patch Attack by using Universal Defensive Frame","created":"2022-04-27","cited_by_count":9,"area":null},{"id":"2102.05241","title":"Detecting Localized Adversarial Examples: A Generic Approach using Critical Region Analysis","created":"2021-02-10","cited_by_count":7,"area":null},{"id":"2405.11547","title":"Certified Robust Accuracy of Neural Networks Are Bounded due to Bayes Errors","created":"2024-05-19","cited_by_count":7,"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":"2306.12610","title":"Revisiting Image Classifier Training for Improved Certified Robust Defense against Adversarial Patches","created":"2023-06-22","cited_by_count":6,"area":null},{"id":"2310.17403","title":"Detection Defenses: An Empty Promise against Adversarial Patch Attacks on Optical Flow","created":"2023-10-26","cited_by_count":6,"area":null},{"id":"2301.11912","title":"OccRob: Efficient SMT-Based Occlusion Robustness Verification of Deep Neural Networks","created":"2023-01-27","cited_by_count":5,"area":null},{"id":"2401.01911","title":"Backdoor Attack on Unpaired Medical Image-Text Foundation Models: A Pilot Study on MedCLIP","created":"2024-01-01","cited_by_count":5,"area":"safety"},{"id":"2406.10285","title":"I Don't Know You, But I Can Catch You: Real-Time Defense against Diverse Adversarial Patches for Object Detectors","created":"2024-06-12","cited_by_count":5,"area":null},{"id":"2409.09406","title":"Real-world Adversarial Defense against Patch Attacks based on Diffusion Model","created":"2024-09-14","cited_by_count":5,"area":"diffusion"},{"id":"2302.04379","title":"Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples","created":"2023-02-09","cited_by_count":4,"area":null},{"id":"2308.15692","title":"Intriguing Properties of Diffusion Models: An Empirical Study of the Natural Attack Capability in Text-to-Image Generative Models","created":"2023-08-30","cited_by_count":4,"area":"diffusion"},{"id":"2403.19080","title":"MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models","created":"2024-03-28","cited_by_count":4,"area":null},{"id":"2410.16317","title":"A Survey on Physical Adversarial Attacks against Face Recognition Systems","created":"2024-10-10","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":"2208.09195","title":"Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks","created":"2022-08-19","cited_by_count":3,"area":null},{"id":"2306.16131","title":"Distributional Modeling for Location-Aware Adversarial Patches","created":"2023-06-28","cited_by_count":3,"area":null},{"id":"2311.17339","title":"RADAP: A Robust and Adaptive Defense Against Diverse Adversarial Patches on Face Recognition","created":"2023-11-29","cited_by_count":3,"area":null},{"id":"2405.07668","title":"CrossCert: A Cross-Checking Detection Approach to Patch Robustness Certification for Deep Learning Models","created":"2024-05-13","cited_by_count":3,"area":null},{"id":"2101.11060","title":"Defenses Against Multi-Sticker Physical Domain Attacks on Classifiers","created":"2021-01-26","cited_by_count":2,"area":null},{"id":"2205.03894","title":"VPN: Verification of Poisoning in Neural Networks","created":"2022-05-08","cited_by_count":2,"area":"safety"},{"id":"2303.08944","title":"Agnostic Multi-Robust Learning Using ERM","created":"2023-03-15","cited_by_count":2,"area":null},{"id":"2308.00452","title":"A Majority Invariant Approach to Patch Robustness Certification for Deep Learning Models","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2309.00879","title":"Towards Certified Probabilistic Robustness with High Accuracy","created":"2023-09-02","cited_by_count":2,"area":null},{"id":"2403.10663","title":"Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2405.14923","title":"How Does Bayes Error Limit Probabilistic Robust Accuracy","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2410.24006","title":"DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination","created":"2024-10-31","cited_by_count":2,"area":"diffusion"},{"id":"2502.09110","title":"Pulling Back the Curtain: Unsupervised Adversarial Detection via Contrastive Auxiliary Networks","created":"2025-02-13","cited_by_count":2,"area":null},{"id":"2205.08989","title":"Defending Object Detectors against Patch Attacks with Out-of-Distribution Smoothing","created":"2022-05-18","cited_by_count":1,"area":null},{"id":"2302.04977","title":"Mithridates: Auditing and Boosting Backdoor Resistance of Machine Learning Pipelines","created":"2023-02-09","cited_by_count":1,"area":null},{"id":"2303.16308","title":"Provable Robustness for Streaming Models with a Sliding Window","created":"2023-03-28","cited_by_count":1,"area":null},{"id":"2304.13919","title":"Detection of Adversarial Physical Attacks in Time-Series Image Data","created":"2023-04-27","cited_by_count":1,"area":null},{"id":"2305.10929","title":"Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches","created":"2023-05-18","cited_by_count":1,"area":null},{"id":"2307.14242","title":"Defending Adversarial Patches via Joint Region Localizing and Inpainting","created":"2023-07-26","cited_by_count":1,"area":null},{"id":"2311.06122","title":"Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches","created":"2023-11-10","cited_by_count":1,"area":null},{"id":"2312.03085","title":"ScAR: Scaling Adversarial Robustness for LiDAR Object Detection","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2405.01349","title":"Position: Towards Resilience Against Adversarial Examples","created":"2024-05-02","cited_by_count":1,"area":null},{"id":"2410.03000","title":"Towards Generalized Certified Robustness with Multi-Norm Training","created":"2024-10-03","cited_by_count":1,"area":null},{"id":"2504.08414","title":"Adversarial Examples in Environment Perception for Automated Driving (Review)","created":"2025-04-11","cited_by_count":1,"area":null},{"id":"2510.04245","title":"Concept-Based Masking: A Patch-Agnostic Defense Against Adversarial Patch Attacks","created":"2025-10-05","cited_by_count":1,"area":null},{"id":"2511.10576","title":"Tight Robustness Certification Through the Convex Hull of $\\ell_0$ Attacks","created":"2025-11-13","cited_by_count":1,"area":null},{"id":"2511.18721","title":"Towards Realistic Guarantees: A Probabilistic Certificate for SmoothLLM","created":"2025-11-24","cited_by_count":1,"area":"safety"},{"id":"2105.00622","title":"Physical world assistive signals for deep neural network classifiers -- neither defense nor attack","created":"2021-05-03","cited_by_count":0,"area":null},{"id":"2106.10324","title":"Group-Structured Adversarial Training","created":"2021-06-18","cited_by_count":0,"area":null},{"id":"2209.02132","title":"Impact of Scaled Image on Robustness of Deep Neural Networks","created":"2022-09-02","cited_by_count":0,"area":null},{"id":"2209.02832","title":"Impact of Colour Variation on Robustness of Deep Neural Networks","created":"2022-09-02","cited_by_count":0,"area":null},{"id":"2311.01563","title":"Assist Is Just as Important as the Goal: Image Resurfacing to Aid Model's Robust Prediction","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2402.04660","title":"Redesigning Traffic Signs to Mitigate Machine-Learning Patch Attacks","created":"2024-02-07","cited_by_count":0,"area":null},{"id":"2409.16726","title":"Formal Local Implication Between Two Neural Networks","created":"2024-09-25","cited_by_count":0,"area":null},{"id":"2503.00563","title":"A Guide to Failure in Machine Learning: Reliability and Robustness from Foundations to Practice","created":"2025-03-01","cited_by_count":0,"area":null},{"id":"2503.06966","title":"MIGA: Mutual Information-Guided Attack on Denoising Models for Semantic Manipulation","created":"2025-03-10","cited_by_count":0,"area":null},{"id":"2505.16318","title":"SuperPure: Efficient Purification of Localized and Distributed Adversarial Patches via Super-Resolution GAN Models","created":"2025-05-22","cited_by_count":0,"area":null},{"id":"2507.23335","title":"Scalable and Precise Patch Robustness Certification for Deep Learning Models with Top-k Predictions","created":"2025-07-31","cited_by_count":0,"area":null},{"id":"2508.10946","title":"IPG: Incremental Patch Generation for Generalized Adversarial Patch Training","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2603.12688","title":"STRAP-ViT: Segregated Tokens with Randomized -- Transformations for Defense against Adversarial Patches in ViTs","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.09746","title":"Hybrid Robustness Verification for Spatio-Temporal Neural Networks","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2606.27694","title":"Halt Fast! Early Stopping for Certified Robustness","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.19351","title":"Uncovering the Limits of Proof Sharing for Neural Networks","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.20791","title":"CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models","created":"2026-08-21","cited_by_count":0,"area":"vla"},{"id":"2609.33513","title":"Printability-Constrained Adversarial Decals for Near-Nadir Aerial Perception: Measured Ink Gamuts, Nested Realism Constraints, and a Physical-World Bound","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":"100"}