{"list":"other","total":56,"rows":[{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1312.6199","title":"Intriguing properties of neural networks","created":"2013-12-21","cited_by_count":5155},{"id":"1610.05820","title":"Membership Inference Attacks against Machine Learning Models","created":"2016-10-18","cited_by_count":2281},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2307.02483","title":"Jailbroken: How Does LLM Safety Training Fail?","created":"2023-07-05","cited_by_count":1651},{"id":"2302.12173","title":"Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection","created":"2023-02-23","cited_by_count":1443},{"id":"2310.08419","title":"Jailbreaking Black Box Large Language Models in Twenty Queries","created":"2023-10-12","cited_by_count":1420},{"id":"2202.03286","title":"Red Teaming Language Models with Language Models","created":"2022-02-07","cited_by_count":1026},{"id":"1602.02697","title":"Practical Black-Box Attacks against Machine Learning","created":"2016-02-08","cited_by_count":903},{"id":"1802.08232","title":"The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks","created":"2018-02-22","cited_by_count":864},{"id":"2301.13188","title":"Extracting Training Data from Diffusion Models","created":"2023-01-30","cited_by_count":732},{"id":"1908.07125","title":"Universal Adversarial Triggers for Attacking and Analyzing NLP","created":"2019-08-20","cited_by_count":722},{"id":"2312.02119","title":"Tree of Attacks: Jailbreaking Black-Box LLMs Automatically","created":"2023-12-04","cited_by_count":672},{"id":"2010.09670","title":"RobustBench: a standardized adversarial robustness benchmark","created":"2020-10-19","cited_by_count":661},{"id":"1609.02943","title":"Stealing Machine Learning Models via Prediction APIs","created":"2016-09-09","cited_by_count":619},{"id":"1806.01246","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","created":"2018-06-04","cited_by_count":498},{"id":"2406.18495","title":"WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs","created":"2024-06-26","cited_by_count":496},{"id":"1704.01155","title":"Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks","created":"2017-04-04","cited_by_count":486},{"id":"1911.02508","title":"Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods","created":"2019-11-06","cited_by_count":443},{"id":"2406.04313","title":"Improving Alignment and Robustness with Circuit Breakers","created":"2024-06-06","cited_by_count":322},{"id":"2306.15447","title":"Are aligned neural networks adversarially aligned?","created":"2023-06-26","cited_by_count":315},{"id":"1812.02766","title":"Knockoff Nets: Stealing Functionality of Black-Box Models","created":"2018-12-06","cited_by_count":292},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285},{"id":"2403.14720","title":"Defending Against Indirect Prompt Injection Attacks With Spotlighting","created":"2024-03-20","cited_by_count":267},{"id":"2104.13733","title":"Gradient-based Adversarial Attacks against Text Transformers","created":"2021-04-15","cited_by_count":234},{"id":"1804.00308","title":"Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning","created":"2018-04-01","cited_by_count":225},{"id":"1906.07983","title":"Explanations can be manipulated and geometry is to blame","created":"2019-06-19","cited_by_count":216},{"id":"1807.01069","title":"Adversarial Robustness Toolbox v1.0.0","created":"2018-07-03","cited_by_count":215},{"id":"2310.10844","title":"Survey of Vulnerabilities in Large Language Models Revealed by Adversarial Attacks","created":"2023-10-16","cited_by_count":194},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186},{"id":"2407.15549","title":"Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs","created":"2024-07-22","cited_by_count":173},{"id":"1709.07886","title":"Machine Learning Models that Remember Too Much","created":"2017-09-22","cited_by_count":169},{"id":"1805.02628","title":"PRADA: Protecting against DNN Model Stealing Attacks","created":"2018-05-07","cited_by_count":165},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148},{"id":"2206.07758","title":"Reconstructing Training Data from Trained Neural Networks","created":"2022-06-15","cited_by_count":133},{"id":"1306.4447","title":"Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifiers","created":"2013-06-19","cited_by_count":130},{"id":"2402.09283","title":"Attacks, Defenses and Evaluations for LLM Conversation Safety: A Survey","created":"2024-02-14","cited_by_count":130},{"id":"1610.00768","title":"Technical Report on the CleverHans v2.1.0 Adversarial Examples Library","created":"2016-10-03","cited_by_count":124},{"id":"1802.05351","title":"Stealing Hyperparameters in Machine Learning","created":"2018-02-14","cited_by_count":118},{"id":"2006.03463","title":"Sponge Examples: Energy-Latency Attacks on Neural Networks","created":"2020-06-05","cited_by_count":111},{"id":"1802.04889","title":"Understanding Membership Inferences on Well-Generalized Learning Models","created":"2018-02-13","cited_by_count":90},{"id":"2307.06865","title":"Effective Prompt Extraction from Language Models","created":"2023-07-13","cited_by_count":85},{"id":"1905.11742","title":"Overlearning Reveals Sensitive Attributes","created":"2019-05-28","cited_by_count":76},{"id":"1806.05476","title":"Copycat CNN: Stealing Knowledge by Persuading Confession with Random Non-Labeled Data","created":"2018-06-14","cited_by_count":70},{"id":"1910.12903","title":"IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary","created":"2019-10-28","cited_by_count":70},{"id":"2007.09339","title":"ML Privacy Meter: Aiding Regulatory Compliance by Quantifying the Privacy Risks of Machine Learning","created":"2020-07-18","cited_by_count":70},{"id":"2302.09923","title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","created":"2023-02-20","cited_by_count":51},{"id":"2105.01622","title":"Poisoning the Unlabeled Dataset of Semi-Supervised Learning","created":"2021-05-04","cited_by_count":44},{"id":"2111.04625","title":"DeepSteal: Advanced Model Extractions Leveraging Efficient Weight Stealing in Memories","created":"2021-11-08","cited_by_count":42},{"id":"2310.15469","title":"The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks","created":"2023-10-24","cited_by_count":36},{"id":"2209.10505","title":"Text Revealer: Private Text Reconstruction via Model Inversion Attacks against Transformers","created":"2022-09-21","cited_by_count":31},{"id":"2203.08147","title":"Energy-Latency Attacks via Sponge Poisoning","created":"2022-03-14","cited_by_count":29},{"id":"2112.00247","title":"Adversarial Attacks Against Deep Generative Models on Data: A Survey","created":"2021-12-01","cited_by_count":24},{"id":"2102.04661","title":"Security and Privacy for Artificial Intelligence: Opportunities and Challenges","created":"2021-02-09","cited_by_count":16},{"id":"2305.03350","title":"Reconstructing Training Data from Multiclass Neural Networks","created":"2023-05-05","cited_by_count":7},{"id":"2005.05823","title":"Perturbing Inputs to Prevent Model Stealing","created":"2020-05-12","cited_by_count":4}],"next_cursor":null}