{"total":158,"rows":[{"id":"2307.15043","title":"Universal and Transferable Adversarial Attacks on Aligned Language Models","created":"2023-07-27","cited_by_count":3104,"area":"alignment"},{"id":"2102.01356","title":"Recent Advances in Adversarial Training for Adversarial Robustness","created":"2021-02-02","cited_by_count":279,"area":null},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185,"area":null},{"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":"2108.04974","title":"SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)","created":"2021-08-11","cited_by_count":69,"area":null},{"id":"2305.10862","title":"How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses","created":"2023-05-18","cited_by_count":66,"area":null},{"id":"2202.08602","title":"Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations","created":"2022-02-17","cited_by_count":61,"area":null},{"id":"2204.11022","title":"Towards Data-Free Model Stealing in a Hard Label Setting","created":"2022-04-23","cited_by_count":58,"area":null},{"id":"2403.09766","title":"An Image Is Worth 1000 Lies: Adversarial Transferability across Prompts on Vision-Language Models","created":"2024-03-14","cited_by_count":45,"area":"mllm"},{"id":"2207.13129","title":"LGV: Boosting Adversarial Example Transferability from Large Geometric Vicinity","created":"2022-07-26","cited_by_count":39,"area":null},{"id":"2104.00671","title":"TRS: Transferability Reduced Ensemble via Encouraging Gradient Diversity and Model Smoothness","created":"2021-04-01","cited_by_count":38,"area":null},{"id":"2110.05922","title":"Trivial or impossible -- dichotomous data difficulty masks model differences (on ImageNet and beyond)","created":"2021-10-12","cited_by_count":35,"area":null},{"id":"2107.02425","title":"GradDiv: Adversarial Robustness of Randomized Neural Networks via Gradient Diversity Regularization","created":"2021-07-06","cited_by_count":34,"area":null},{"id":"2210.09194","title":"Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class","created":"2022-10-17","cited_by_count":33,"area":null},{"id":"2106.04938","title":"Attacking Adversarial Attacks as A Defense","created":"2021-06-09","cited_by_count":32,"area":null},{"id":"2103.04302","title":"Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain","created":"2021-03-07","cited_by_count":29,"area":null},{"id":"2104.01575","title":"Reliably fast adversarial training via latent adversarial perturbation","created":"2021-04-04","cited_by_count":29,"area":null},{"id":"2301.00364","title":"Generalizable Black-Box Adversarial Attack with Meta Learning","created":"2023-01-01","cited_by_count":29,"area":null},{"id":"2103.05266","title":"BASAR:Black-box Attack on Skeletal Action Recognition","created":"2021-03-09","cited_by_count":26,"area":null},{"id":"2305.04701","title":"Differentially Private Attention Computation","created":"2023-05-08","cited_by_count":25,"area":null},{"id":"2103.05347","title":"Understanding the Robustness of Skeleton-based Action Recognition under Adversarial Attack","created":"2021-03-09","cited_by_count":24,"area":null},{"id":"2107.04570","title":"ANCER: Anisotropic Certification via Sample-wise Volume Maximization","created":"2021-07-09","cited_by_count":23,"area":null},{"id":"2410.23687","title":"Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey","created":"2024-10-31","cited_by_count":23,"area":"mllm"},{"id":"2102.06905","title":"Mixed Nash Equilibria in the Adversarial Examples Game","created":"2021-02-13","cited_by_count":22,"area":null},{"id":"2112.14337","title":"Closer Look at the Transferability of Adversarial Examples: How They Fool Different Models Differently","created":"2021-12-29","cited_by_count":22,"area":null},{"id":"2505.05528","title":"X-Transfer Attacks: Towards Super Transferable Adversarial Attacks on CLIP","created":"2025-05-08","cited_by_count":21,"area":"mllm"},{"id":"2105.10843","title":"Exploring Robustness of Unsupervised Domain Adaptation in Semantic Segmentation","created":"2021-05-23","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":"2212.05680","title":"REAP: A Large-Scale Realistic Adversarial Patch Benchmark","created":"2022-12-12","cited_by_count":18,"area":null},{"id":"2110.15053","title":"Adversarial Robustness in Multi-Task Learning: Promises and Illusions","created":"2021-10-26","cited_by_count":17,"area":null},{"id":"2112.05005","title":"Mutual Adversarial Training: Learning together is better than going alone","created":"2021-12-09","cited_by_count":17,"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":"2206.09098","title":"Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classification","created":"2022-06-18","cited_by_count":15,"area":null},{"id":"2307.15008","title":"A LLM Assisted Exploitation of AI-Guardian","created":"2023-07-20","cited_by_count":15,"area":null},{"id":"2211.14860","title":"Foiling Explanations in Deep Neural Networks","created":"2022-11-27","cited_by_count":14,"area":null},{"id":"2212.09035","title":"Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks","created":"2022-12-18","cited_by_count":14,"area":null},{"id":"2105.08619","title":"On the Robustness of Domain Constraints","created":"2021-05-18","cited_by_count":11,"area":null},{"id":"2202.05687","title":"D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles","created":"2022-02-11","cited_by_count":11,"area":null},{"id":"2105.12419","title":"Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge","created":"2021-05-26","cited_by_count":10,"area":null},{"id":"2206.03351","title":"AS2T: Arbitrary Source-To-Target Adversarial Attack on Speaker Recognition Systems","created":"2022-06-07","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":"2403.06014","title":"Hard-label based Small Query Black-box Adversarial Attack","created":"2024-03-09","cited_by_count":10,"area":null},{"id":"2405.20775","title":"Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models","created":"2024-05-26","cited_by_count":10,"area":"mllm"},{"id":"2102.13184","title":"Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks","created":"2021-02-25","cited_by_count":9,"area":null},{"id":"2108.02707","title":"Fairness Properties of Face Recognition and Obfuscation Systems","created":"2021-08-05","cited_by_count":9,"area":null},{"id":"2110.04488","title":"Demystifying the Transferability of Adversarial Attacks in Computer Networks","created":"2021-10-09","cited_by_count":9,"area":null},{"id":"2206.09238","title":"On the Role of Generalization in Transferability of Adversarial Examples","created":"2022-06-18","cited_by_count":9,"area":null},{"id":"2207.04129","title":"How many perturbations break this model? Evaluating robustness beyond adversarial accuracy","created":"2022-07-08","cited_by_count":9,"area":null},{"id":"2106.06056","title":"Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation","created":"2021-06-10","cited_by_count":8,"area":null},{"id":"2109.11125","title":"Adversarial Transfer Attacks With Unknown Data and Class Overlap","created":"2021-09-23","cited_by_count":8,"area":null},{"id":"2110.11950","title":"Adversarial robustness for latent models: Revisiting the robust-standard accuracies tradeoff","created":"2021-10-22","cited_by_count":8,"area":null},{"id":"2110.14735","title":"Towards Evaluating the Robustness of Neural Networks Learned by Transduction","created":"2021-10-27","cited_by_count":8,"area":null},{"id":"2102.04450","title":"Noise Optimization for Artificial Neural Networks","created":"2021-02-06","cited_by_count":7,"area":null},{"id":"2102.05110","title":"Adversarial Perturbations Are Not So Weird: Entanglement of Robust and Non-Robust Features in Neural Network Classifiers","created":"2021-02-09","cited_by_count":7,"area":null},{"id":"2211.11312","title":"Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack","created":"2022-11-21","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":"2408.08671","title":"Towards Physical World Backdoor Attacks against Skeleton Action Recognition","created":"2024-08-16","cited_by_count":7,"area":null},{"id":"2410.06851","title":"Understanding Model Ensemble in Transferable Adversarial Attack","created":"2024-10-09","cited_by_count":7,"area":null},{"id":"2108.12492","title":"Disrupting Adversarial Transferability in Deep Neural Networks","created":"2021-08-27","cited_by_count":6,"area":null},{"id":"2203.10502","title":"Adversarial Parameter Attack on Deep Neural Networks","created":"2022-03-20","cited_by_count":6,"area":null},{"id":"2306.16050","title":"Evaluating Similitude and Robustness of Deep Image Denoising Models via Adversarial Attack","created":"2023-06-28","cited_by_count":6,"area":null},{"id":"2307.04042","title":"Sup-Norm Convergence of Deep Neural Network Estimator for Nonparametric Regression by Adversarial Training","created":"2023-07-08","cited_by_count":6,"area":null},{"id":"2312.03245","title":"A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System","created":"2023-12-06","cited_by_count":6,"area":null},{"id":"2205.02414","title":"Subverting Fair Image Search with Generative Adversarial Perturbations","created":"2022-05-05","cited_by_count":5,"area":null},{"id":"2209.00005","title":"Be Your Own Neighborhood: Detecting Adversarial Example by the Neighborhood Relations Built on Self-Supervised Learning","created":"2022-08-31","cited_by_count":5,"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":"2312.13118","title":"LRS: Enhancing Adversarial Transferability through Lipschitz Regularized Surrogate","created":"2023-12-20","cited_by_count":5,"area":null},{"id":"2210.11407","title":"Similarity of Neural Architectures using Adversarial Attack Transferability","created":"2022-10-20","cited_by_count":4,"area":null},{"id":"2310.17584","title":"A minimax optimal control approach for robust neural ODEs","created":"2023-10-26","cited_by_count":4,"area":null},{"id":"2406.10573","title":"Graph Neural Backdoor: Fundamentals, Methodologies, Applications, and Future Directions","created":"2024-06-15","cited_by_count":4,"area":null},{"id":"2601.22359","title":"The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples","created":"2026-01-29","cited_by_count":4,"area":"safety"},{"id":"2103.02014","title":"Online Adversarial Attacks","created":"2021-03-02","cited_by_count":3,"area":null},{"id":"2203.11849","title":"A Girl Has A Name, And It's ... Adversarial Authorship Attribution for Deobfuscation","created":"2022-03-22","cited_by_count":3,"area":null},{"id":"2208.14302","title":"A Black-Box Attack on Optical Character Recognition Systems","created":"2022-08-30","cited_by_count":3,"area":null},{"id":"2211.02675","title":"An Adversarial Robustness Perspective on the Topology of Neural Networks","created":"2022-11-04","cited_by_count":3,"area":null},{"id":"2308.08160","title":"Benchmarking Adversarial Robustness of Compressed Deep Learning Models","created":"2023-08-16","cited_by_count":3,"area":null},{"id":"2309.01104","title":"Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection","created":"2023-09-03","cited_by_count":3,"area":null},{"id":"2402.15586","title":"Distilling Adversarial Robustness Using Heterogeneous Teachers","created":"2024-02-23","cited_by_count":3,"area":"distill"},{"id":"2502.20562","title":"LISArD: Learning Image Similarity to Defend Against Gray-box Adversarial Attacks","created":"2025-02-27","cited_by_count":3,"area":null},{"id":"2106.08387","title":"Towards Adversarial Robustness via Transductive Learning","created":"2021-06-15","cited_by_count":2,"area":null},{"id":"2111.04404","title":"Robust and Information-theoretically Safe Bias Classifier against Adversarial Attacks","created":"2021-11-08","cited_by_count":2,"area":null},{"id":"2207.13036","title":"Jacobian Norm with Selective Input Gradient Regularization for Improved and Interpretable Adversarial Defense","created":"2022-07-09","cited_by_count":2,"area":null},{"id":"2307.14751","title":"FLARE: Fingerprinting Deep Reinforcement Learning Agents using Universal Adversarial Masks","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2308.00311","title":"Doubly Robust Instance-Reweighted Adversarial Training","created":"2023-08-01","cited_by_count":2,"area":null},{"id":"2412.20987","title":"RobustBlack: Challenging Black-Box Adversarial Attacks on State-of-the-Art Defenses","created":"2024-12-30","cited_by_count":2,"area":null},{"id":"2502.17003","title":"Information-Geometric Inverse Distillation for Enhancing Adversarial Transferability","created":"2025-02-24","cited_by_count":2,"area":null},{"id":"2506.02711","title":"Privacy Leaks by Adversaries: Adversarial Iterations for Membership Inference Attack","created":"2025-06-03","cited_by_count":2,"area":"safety"},{"id":"2509.23689","title":"Merge Now, Regret Later: The Hidden Cost of Model Merging Is Adversarial Transferability","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2510.03224","title":"Test-Time Defense Against Adversarial Attacks via Stochastic Resonance of Latent Ensembles","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2511.12985","title":"Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks","created":"2025-11-17","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":"2106.10996","title":"Delving into the pixels of adversarial samples","created":"2021-06-21","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":"2109.05558","title":"CoG: a Two-View Co-training Framework for Defending Adversarial Attacks on Graph","created":"2021-09-12","cited_by_count":1,"area":null},{"id":"2109.05919","title":"Evolving Architectures with Gradient Misalignment toward Low Adversarial Transferability","created":"2021-09-13","cited_by_count":1,"area":null},{"id":"2110.11597","title":"ProtoShotXAI: Using Prototypical Few-Shot Architecture for Explainable AI","created":"2021-10-22","cited_by_count":1,"area":null},{"id":"2205.15357","title":"Searching for the Essence of Adversarial Perturbations","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2206.00772","title":"On the reversibility of adversarial attacks","created":"2022-06-01","cited_by_count":1,"area":null},{"id":"2206.08124","title":"Using adversarial images to improve outcomes of federated learning for non-IID data","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2208.10878","title":"Transferability Ranking of Adversarial Examples","created":"2022-08-23","cited_by_count":1,"area":null}],"next_cursor":"100"}