{"total":259,"rows":[{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651,"area":"safety"},{"id":"2210.10760","title":"Scaling Laws for Reward Model Overoptimization","created":"2022-10-19","cited_by_count":1095,"area":"alignment"},{"id":"2110.01167","title":"Trustworthy AI: From Principles to Practices","created":"2021-10-04","cited_by_count":207,"area":null},{"id":"2103.10689","title":"Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond","created":"2021-03-19","cited_by_count":118,"area":null},{"id":"2112.06409","title":"Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective","created":"2021-12-13","cited_by_count":116,"area":null},{"id":"2102.13620","title":"Towards Robust and Reliable Algorithmic Recourse","created":"2021-02-26","cited_by_count":102,"area":null},{"id":"2401.08573","title":"WAVES: Benchmarking the Robustness of Image Watermarks","created":"2024-01-16","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":"2107.06641","title":"Trustworthy AI: A Computational Perspective","created":"2021-07-12","cited_by_count":93,"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":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2210.07321","title":"Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods","created":"2022-10-13","cited_by_count":79,"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":"2502.14881","title":"A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations","created":"2025-02-14","cited_by_count":67,"area":"mllm"},{"id":"2106.07904","title":"Probabilistic Margins for Instance Reweighting in Adversarial Training","created":"2021-06-15","cited_by_count":57,"area":null},{"id":"2101.02032","title":"Socially Responsible AI Algorithms: Issues, Purposes, and Challenges","created":"2021-01-01","cited_by_count":56,"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":"2203.08392","title":"Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?","created":"2022-03-16","cited_by_count":49,"area":null},{"id":"2107.01614","title":"Survey: Leakage and Privacy at Inference Time","created":"2021-07-04","cited_by_count":44,"area":null},{"id":"2106.03734","title":"Reveal of Vision Transformers Robustness against Adversarial Attacks","created":"2021-06-07","cited_by_count":43,"area":null},{"id":"2210.05927","title":"Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learning","created":"2022-10-12","cited_by_count":43,"area":null},{"id":"2402.14433","title":"A Language Model's Guide Through Latent Space","created":"2024-02-22","cited_by_count":43,"area":null},{"id":"2208.03160","title":"Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz Networks","created":"2022-08-05","cited_by_count":39,"area":null},{"id":"2403.13682","title":"Threats, Attacks, and Defenses in Machine Unlearning: A Survey","created":"2024-03-20","cited_by_count":39,"area":"safety"},{"id":"2106.15764","title":"The Threat of Offensive AI to Organizations","created":"2021-06-30","cited_by_count":38,"area":null},{"id":"2107.10137","title":"Improved Text Classification via Contrastive Adversarial Training","created":"2021-07-21","cited_by_count":38,"area":null},{"id":"2305.12090","title":"UP5: Unbiased Foundation Model for Fairness-aware Recommendation","created":"2023-05-20","cited_by_count":38,"area":null},{"id":"2402.09177","title":"Leveraging the Context through Multi-Round Interactions for Jailbreaking Attacks","created":"2024-02-14","cited_by_count":36,"area":"safety"},{"id":"2207.09504","title":"Invariant Feature Learning for Generalized Long-Tailed Classification","created":"2022-07-19","cited_by_count":34,"area":null},{"id":"2212.05630","title":"DISCO: Adversarial Defense with Local Implicit Functions","created":"2022-12-11","cited_by_count":34,"area":null},{"id":"2403.12404","title":"Understanding and Improving Training-free Loss-based Diffusion Guidance","created":"2024-03-19","cited_by_count":32,"area":"diffusion"},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30,"area":null},{"id":"2403.18249","title":"Exploring the Deceptive Power of LLM-Generated Fake News: A Study of Real-World Detection Challenges","created":"2024-03-27","cited_by_count":30,"area":null},{"id":"2110.14068","title":"Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks","created":"2021-10-26","cited_by_count":29,"area":null},{"id":"2105.07091","title":"Verification of Image-based Neural Network Controllers Using Generative Models","created":"2021-05-14","cited_by_count":27,"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":"2405.13077","title":"GPT-4 Jailbreaks Itself with Near-Perfect Success Using Self-Explanation","created":"2024-05-21","cited_by_count":25,"area":"safety"},{"id":"2106.08361","title":"Adversarial Attacks on Deep Models for Financial Transaction Records","created":"2021-06-15","cited_by_count":24,"area":null},{"id":"2305.02279","title":"Learngene: Inheriting Condensed Knowledge from the Ancestry Model to Descendant Models","created":"2023-05-03","cited_by_count":24,"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":"2203.06414","title":"A Survey of Adversarial Defences and Robustness in NLP","created":"2022-03-12","cited_by_count":23,"area":null},{"id":"2205.02392","title":"Robust Conversational Agents against Imperceptible Toxicity Triggers","created":"2022-05-05","cited_by_count":23,"area":"agents"},{"id":"2103.00429","title":"Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models","created":"2021-02-28","cited_by_count":22,"area":null},{"id":"2201.08619","title":"Dangerous Cloaking: Natural Trigger based Backdoor Attacks on Object Detectors in the Physical World","created":"2022-01-21","cited_by_count":22,"area":null},{"id":"2203.05314","title":"SoK: On the Semantic AI Security in Autonomous Driving","created":"2022-03-10","cited_by_count":22,"area":null},{"id":"2309.10544","title":"Model Leeching: An Extraction Attack Targeting LLMs","created":"2023-09-19","cited_by_count":22,"area":null},{"id":"2305.06024","title":"A Survey on the Robustness of Computer Vision Models against Common Corruptions","created":"2023-05-10","cited_by_count":21,"area":null},{"id":"2110.08932","title":"Poisoning Attacks on Fair Machine Learning","created":"2021-10-17","cited_by_count":19,"area":null},{"id":"2207.00425","title":"Transferable Graph Backdoor Attack","created":"2022-06-21","cited_by_count":19,"area":null},{"id":"2112.12310","title":"Adversarial Attacks against Windows PE Malware Detection: A Survey of the State-of-the-Art","created":"2021-12-23","cited_by_count":18,"area":null},{"id":"2410.08190","title":"Poison-splat: Computation Cost Attack on 3D Gaussian Splatting","created":"2024-10-10","cited_by_count":18,"area":null},{"id":"2202.01263","title":"NoisyMix: Boosting Model Robustness to Common Corruptions","created":"2022-02-02","cited_by_count":17,"area":null},{"id":"2203.15230","title":"Zero-Query Transfer Attacks on Context-Aware Object Detectors","created":"2022-03-29","cited_by_count":17,"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":"2212.02531","title":"Enhancing Quantum Adversarial Robustness by Randomized Encodings","created":"2022-12-05","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":"2506.06151","title":"Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems","created":"2025-06-06","cited_by_count":16,"area":"rag"},{"id":"2112.02625","title":"Explainable Deep Learning in Healthcare: A Methodological Survey from an Attribution View","created":"2021-12-05","cited_by_count":15,"area":null},{"id":"2210.02713","title":"On Optimal Learning Under Targeted Data Poisoning","created":"2022-10-06","cited_by_count":14,"area":"safety"},{"id":"2302.03225","title":"Efficient XAI Techniques: A Taxonomic Survey","created":"2023-02-07","cited_by_count":14,"area":null},{"id":"2401.14440","title":"Semantic Sensitivities and Inconsistent Predictions: Measuring the Fragility of NLI Models","created":"2024-01-25","cited_by_count":14,"area":null},{"id":"2111.10130","title":"Fooling Adversarial Training with Inducing Noise","created":"2021-11-19","cited_by_count":13,"area":null},{"id":"2203.10939","title":"Deep Learning Serves Traffic Safety Analysis: A Forward-looking Review","created":"2022-03-07","cited_by_count":13,"area":null},{"id":"2407.12443","title":"Preventing Catastrophic Overfitting in Fast Adversarial Training: A Bi-level Optimization Perspective","created":"2024-07-17","cited_by_count":13,"area":null},{"id":"2105.14644","title":"Generating Adversarial Examples with Graph Neural Networks","created":"2021-05-30","cited_by_count":12,"area":null},{"id":"2301.12576","title":"Uncovering Adversarial Risks of Test-Time Adaptation","created":"2023-01-29","cited_by_count":12,"area":null},{"id":"2408.05446","title":"Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness","created":"2024-08-08","cited_by_count":12,"area":null},{"id":"2503.10809","title":"MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents","created":"2025-03-13","cited_by_count":12,"area":"agents"},{"id":"2103.14739","title":"Leaky Nets: Recovering Embedded Neural Network Models and Inputs through Simple Power and Timing Side-Channels -- Attacks and Defenses","created":"2021-03-26","cited_by_count":11,"area":null},{"id":"2107.13639","title":"Imbalanced Adversarial Training with Reweighting","created":"2021-07-28","cited_by_count":11,"area":null},{"id":"2112.06654","title":"Toward Open-World Electroencephalogram Decoding Via Deep Learning: A Comprehensive Survey","created":"2021-12-08","cited_by_count":11,"area":null},{"id":"2201.00768","title":"Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions","created":"2022-01-03","cited_by_count":11,"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":"2402.02629","title":"PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks","created":"2024-02-04","cited_by_count":11,"area":null},{"id":"2407.18454","title":"Fairness Definitions in Language Models Explained","created":"2024-07-26","cited_by_count":11,"area":null},{"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":"2110.07034","title":"How Does Momentum Benefit Deep Neural Networks Architecture Design? A Few Case Studies","created":"2021-10-13","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},{"id":"2306.06359","title":"NeRFool: Uncovering the Vulnerability of Generalizable Neural Radiance Fields against Adversarial Perturbations","created":"2023-06-10","cited_by_count":10,"area":null},{"id":"2107.05911","title":"Model Transferability With Responsive Decision Subjects","created":"2021-07-13","cited_by_count":9,"area":null},{"id":"2202.03071","title":"Distributionally Robust Fair Principal Components via Geodesic Descents","created":"2022-02-07","cited_by_count":9,"area":null},{"id":"2202.07260","title":"Learning Disentangled Behaviour Patterns for Wearable-based Human Activity Recognition","created":"2022-02-15","cited_by_count":9,"area":null},{"id":"2203.04713","title":"Defending Black-box Skeleton-based Human Activity Classifiers","created":"2022-03-09","cited_by_count":9,"area":null},{"id":"2303.09767","title":"It Is All About Data: A Survey on the Effects of Data on Adversarial Robustness","created":"2023-03-17","cited_by_count":9,"area":null},{"id":"2312.16113","title":"Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Prediction","created":"2023-12-20","cited_by_count":9,"area":"distill"},{"id":"2406.10427","title":"Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step Defences","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2207.05225","title":"Susceptibility of Continual Learning Against Adversarial Attacks","created":"2022-07-11","cited_by_count":8,"area":null},{"id":"2305.06472","title":"ChatGPT-Like Large-Scale Foundation Models for Prognostics and Health Management: A Survey and Roadmaps","created":"2023-05-10","cited_by_count":8,"area":null},{"id":"2401.15568","title":"Intriguing Equivalence Structures of the Embedding Space of Vision Transformers","created":"2024-01-28","cited_by_count":8,"area":null},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2410.22888","title":"Effective and Efficient Adversarial Detection for Vision-Language Models via A Single Vector","created":"2024-10-30","cited_by_count":8,"area":"mllm"},{"id":"2503.20613","title":"State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning","created":"2025-03-26","cited_by_count":8,"area":"deeprl"},{"id":"2111.01714","title":"Meta-Learning the Search Distribution of Black-Box Random Search Based Adversarial Attacks","created":"2021-11-02","cited_by_count":7,"area":null},{"id":"2202.09994","title":"Transferring Adversarial Robustness Through Robust Representation Matching","created":"2022-02-21","cited_by_count":7,"area":null},{"id":"2206.10158","title":"Certifiably Robust Policy Learning against Adversarial Communication in Multi-agent Systems","created":"2022-06-21","cited_by_count":7,"area":null},{"id":"2207.00694","title":"Efficient Adversarial Training With Data Pruning","created":"2022-07-01","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":"2403.10492","title":"Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning","created":"2024-03-15","cited_by_count":7,"area":"mllm"},{"id":"2503.20844","title":"Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks","created":"2025-03-26","cited_by_count":7,"area":"deeprl"},{"id":"2102.01979","title":"Key Technology Considerations in Developing and Deploying Machine Learning Models in Clinical Radiology Practice","created":"2021-02-03","cited_by_count":6,"area":null}],"next_cursor":"100"}