{"total":414,"rows":[{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797,"area":null},{"id":"2404.02151","title":"Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks","created":"2024-04-02","cited_by_count":486,"area":"safety"},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249,"area":null},{"id":"2108.10241","title":"Back to the Drawing Board: A Critical Evaluation of Poisoning Attacks on Production Federated Learning","created":"2021-08-23","cited_by_count":118,"area":null},{"id":"2104.09425","title":"Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?","created":"2021-04-19","cited_by_count":113,"area":null},{"id":"2102.11436","title":"Model-Based Domain Generalization","created":"2021-02-23","cited_by_count":104,"area":null},{"id":"2106.04732","title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","created":"2021-06-08","cited_by_count":104,"area":null},{"id":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97,"area":null},{"id":"2205.01992","title":"Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning","created":"2022-05-04","cited_by_count":94,"area":"safety"},{"id":"2103.05633","title":"Proof-of-Learning: Definitions and Practice","created":"2021-03-09","cited_by_count":84,"area":null},{"id":"2407.07403","title":"A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trends","created":"2024-07-10","cited_by_count":84,"area":"mllm"},{"id":"2407.11969","title":"Does Refusal Training in LLMs Generalize to the Past Tense?","created":"2024-07-16","cited_by_count":79,"area":"safety"},{"id":"2106.15831","title":"The Evolution of Out-of-Distribution Robustness Throughout Fine-Tuning","created":"2021-06-30","cited_by_count":75,"area":null},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75,"area":null},{"id":"2103.13127","title":"Black-box Detection of Backdoor Attacks with Limited Information and Data","created":"2021-03-24","cited_by_count":73,"area":null},{"id":"2106.09898","title":"Bad Characters: Imperceptible NLP Attacks","created":"2021-06-18","cited_by_count":71,"area":null},{"id":"1910.05821","title":"Policy Poisoning in Batch Reinforcement Learning and Control","created":"2019-10-13","cited_by_count":70,"area":"offlinerl"},{"id":"2207.09944","title":"Probable Domain Generalization via Quantile Risk Minimization","created":"2022-07-20","cited_by_count":66,"area":null},{"id":"2111.00898","title":"Availability Attacks Create Shortcuts","created":"2021-11-01","cited_by_count":62,"area":null},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62,"area":"safety"},{"id":"2102.04716","title":"Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Training","created":"2021-02-09","cited_by_count":59,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"area":null},{"id":"2205.06900","title":"MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic","created":"2022-05-13","cited_by_count":55,"area":null},{"id":"2105.00203","title":"Adversarial Example Detection for DNN Models: A Review and Experimental Comparison","created":"2021-05-01","cited_by_count":52,"area":null},{"id":"2102.12827","title":"Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints","created":"2021-02-25","cited_by_count":50,"area":null},{"id":"2306.06123","title":"Adversarial attacks and defenses in explainable artificial intelligence: A survey","created":"2023-06-06","cited_by_count":48,"area":null},{"id":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2202.01181","title":"Make Some Noise: Reliable and Efficient Single-Step Adversarial Training","created":"2022-02-02","cited_by_count":43,"area":null},{"id":"2101.02559","title":"Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead","created":"2021-01-04","cited_by_count":41,"area":null},{"id":"2312.05355","title":"Neither hype nor gloom do DNNs justice","created":"2023-12-08","cited_by_count":40,"area":null},{"id":"2406.06822","title":"An LLM-Assisted Easy-to-Trigger Backdoor Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection","created":"2024-06-10","cited_by_count":40,"area":"safety"},{"id":"2204.01738","title":"Experimental quantum adversarial learning with programmable superconducting qubits","created":"2022-04-04","cited_by_count":39,"area":null},{"id":"2106.15764","title":"The Threat of Offensive AI to Organizations","created":"2021-06-30","cited_by_count":38,"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":"2301.01217","title":"Unlearnable Clusters: Towards Label-agnostic Unlearnable Examples","created":"2022-12-31","cited_by_count":36,"area":null},{"id":"2303.15735","title":"Improving the Transferability of Adversarial Samples by Path-Augmented Method","created":"2023-03-28","cited_by_count":36,"area":null},{"id":"2108.13421","title":"Recent advances for quantum classifiers","created":"2021-08-30","cited_by_count":35,"area":null},{"id":"2202.11202","title":"Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning","created":"2022-02-22","cited_by_count":34,"area":"safety"},{"id":"2105.03592","title":"De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks","created":"2021-05-08","cited_by_count":33,"area":"safety"},{"id":"2103.02093","title":"Pseudo-labeling for Scalable 3D Object Detection","created":"2021-03-02","cited_by_count":32,"area":null},{"id":"2203.09702","title":"Federated Learning for Privacy Preservation in Smart Healthcare Systems: A Comprehensive Survey","created":"2022-03-18","cited_by_count":31,"area":null},{"id":"2203.08147","title":"Energy-Latency Attacks via Sponge Poisoning","created":"2022-03-14","cited_by_count":29,"area":null},{"id":"2306.15427","title":"Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions","created":"2023-06-27","cited_by_count":28,"area":null},{"id":"2405.16134","title":"Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack","created":"2024-05-25","cited_by_count":28,"area":null},{"id":"2102.05289","title":"Bayesian Inference with Certifiable Adversarial Robustness","created":"2021-02-10","cited_by_count":26,"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":"2206.07840","title":"Architectural Backdoors in Neural Networks","created":"2022-06-15","cited_by_count":25,"area":null},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2102.07788","title":"Universal Adversarial Examples and Perturbations for Quantum Classifiers","created":"2021-02-15","cited_by_count":23,"area":null},{"id":"2106.09947","title":"Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examples","created":"2021-06-18","cited_by_count":23,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2206.09707","title":"The Role of Machine Learning in Cybersecurity","created":"2022-06-20","cited_by_count":22,"area":null},{"id":"2102.05776","title":"Defense Against Reward Poisoning Attacks in Reinforcement Learning","created":"2021-02-10","cited_by_count":21,"area":null},{"id":"2204.06274","title":"Overparameterized Linear Regression under Adversarial Attacks","created":"2022-04-13","cited_by_count":21,"area":null},{"id":"2207.05164","title":"Machine Learning Security in Industry: A Quantitative Survey","created":"2022-07-11","cited_by_count":21,"area":null},{"id":"2105.04404","title":"Topological Uncertainty: Monitoring trained neural networks through persistence of activation graphs","created":"2021-05-07","cited_by_count":20,"area":null},{"id":"2208.10605","title":"SoK: Explainable Machine Learning for Computer Security Applications","created":"2022-08-22","cited_by_count":20,"area":null},{"id":"2306.06209","title":"Backdoor Attack with Sparse and Invisible Trigger","created":"2023-05-11","cited_by_count":20,"area":null},{"id":"2303.08500","title":"The Devil's Advocate: Shattering the Illusion of Unexploitable Data using Diffusion Models","created":"2023-03-15","cited_by_count":19,"area":"diffusion"},{"id":"2102.06004","title":"Fairness-Aware PAC Learning from Corrupted Data","created":"2021-02-11","cited_by_count":18,"area":null},{"id":"2207.03586","title":"CausalAgents: A Robustness Benchmark for Motion Forecasting using Causal Relationships","created":"2022-07-07","cited_by_count":18,"area":null},{"id":"2406.05670","title":"Certified Robustness to Data Poisoning in Gradient-Based Training","created":"2024-06-09","cited_by_count":18,"area":"safety"},{"id":"2212.02531","title":"Enhancing Quantum Adversarial Robustness by Randomized Encodings","created":"2022-12-05","cited_by_count":17,"area":null},{"id":"2311.09994","title":"Towards more Practical Threat Models in Artificial Intelligence Security","created":"2023-11-16","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":"2103.01895","title":"Adversarial Examples can be Effective Data Augmentation for Unsupervised Machine Learning","created":"2021-03-02","cited_by_count":16,"area":null},{"id":"2109.15031","title":"Back in Black: A Comparative Evaluation of Recent State-Of-The-Art Black-Box Attacks","created":"2021-09-29","cited_by_count":16,"area":null},{"id":"2111.03120","title":"Adversarial Attacks on Knowledge Graph Embeddings via Instance Attribution Methods","created":"2021-11-04","cited_by_count":16,"area":"safety"},{"id":"2202.10276","title":"Poisoning Attacks and Defenses on Artificial Intelligence: A Survey","created":"2022-02-21","cited_by_count":16,"area":"safety"},{"id":"2212.11119","title":"A survey on text generation using generative adversarial networks","created":"2022-12-20","cited_by_count":16,"area":null},{"id":"2512.12594","title":"ceLLMate: Sandboxing Browser AI Agents","created":"2025-12-14","cited_by_count":16,"area":"safety"},{"id":"2208.13058","title":"Adversarial Robustness for Tabular Data through Cost and Utility Awareness","created":"2022-08-27","cited_by_count":15,"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":"2212.05056","title":"Testing Human Ability To Detect Deepfake Images of Human Faces","created":"2022-12-07","cited_by_count":15,"area":null},{"id":"2410.04772","title":"From Transparency to Accountability and Back: A Discussion of Access and Evidence in AI Auditing","created":"2024-10-07","cited_by_count":15,"area":null},{"id":"2110.02929","title":"Adversarial Attacks on Spiking Convolutional Neural Networks for Event-based Vision","created":"2021-10-06","cited_by_count":14,"area":null},{"id":"2404.19460","title":"AttackBench: Evaluating Gradient-based Attacks for Adversarial Examples","created":"2024-04-30","cited_by_count":14,"area":null},{"id":"2108.11673","title":"Why Adversarial Reprogramming Works, When It Fails, and How to Tell the Difference","created":"2021-08-26","cited_by_count":13,"area":null},{"id":"2201.12765","title":"Improving Robustness by Enhancing Weak Subnets","created":"2022-01-30","cited_by_count":13,"area":null},{"id":"2305.00550","title":"SoK: Pragmatic Assessment of Machine Learning for Network Intrusion Detection","created":"2023-04-30","cited_by_count":13,"area":null},{"id":"2106.13997","title":"The Feasibility and Inevitability of Stealth Attacks","created":"2021-06-26","cited_by_count":12,"area":null},{"id":"2108.01644","title":"The Devil is in the GAN: Backdoor Attacks and Defenses in Deep Generative Models","created":"2021-08-03","cited_by_count":12,"area":"safety"},{"id":"2111.06345","title":"Poisoning Knowledge Graph Embeddings via Relation Inference Patterns","created":"2021-11-11","cited_by_count":12,"area":"safety"},{"id":"2201.13329","title":"Can Adversarial Training Be Manipulated By Non-Robust Features?","created":"2022-01-31","cited_by_count":12,"area":null},{"id":"2203.09739","title":"Do Deep Networks Transfer Invariances Across Classes?","created":"2022-03-18","cited_by_count":12,"area":null},{"id":"2205.04525","title":"Towards a multi-stakeholder value-based assessment framework for algorithmic systems","created":"2022-05-09","cited_by_count":12,"area":null},{"id":"2207.06154","title":"On the Robustness of Bayesian Neural Networks to Adversarial Attacks","created":"2022-07-13","cited_by_count":12,"area":null},{"id":"2210.00430","title":"Understanding Adversarial Robustness Against On-manifold Adversarial Examples","created":"2022-10-02","cited_by_count":12,"area":null},{"id":"2402.04010","title":"Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously","created":"2024-02-06","cited_by_count":12,"area":null},{"id":"2403.20254","title":"Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptions","created":"2024-03-29","cited_by_count":12,"area":null},{"id":"2104.09981","title":"Prospective Artificial Intelligence Approaches for Active Cyber Defence","created":"2021-04-20","cited_by_count":11,"area":null},{"id":"2105.00227","title":"On the Adversarial Robustness of Quantized Neural Networks","created":"2021-05-01","cited_by_count":11,"area":null},{"id":"2105.08619","title":"On the Robustness of Domain Constraints","created":"2021-05-18","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":"2604.23338","title":"A Systematic Survey of Security Threats and Defenses in LLM-Based AI Agents: A Layered Attack Surface Framework","created":"2026-04-25","cited_by_count":11,"area":"agents"},{"id":"2102.07244","title":"Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS","created":"2021-02-14","cited_by_count":10,"area":null},{"id":"2104.09437","title":"Provable Robustness of Adversarial Training for Learning Halfspaces with Noise","created":"2021-04-19","cited_by_count":10,"area":null},{"id":"2106.14815","title":"Feature Importance Guided Attack: A Model Agnostic Adversarial Attack","created":"2021-06-28","cited_by_count":10,"area":null},{"id":"2201.02354","title":"GenLabel: Mixup Relabeling using Generative Models","created":"2022-01-07","cited_by_count":10,"area":null}],"next_cursor":"100"}