{"total":22,"rows":[{"id":"2309.13788","title":"Can LLM-Generated Misinformation Be Detected?","created":"2023-09-25","cited_by_count":177,"area":null},{"id":"2307.05845","title":"PIGEON: Predicting Image Geolocations","created":"2023-07-11","cited_by_count":56,"area":null},{"id":"2412.07097","title":"On Evaluating the Durability of Safeguards for Open-Weight LLMs","created":"2024-12-10","cited_by_count":52,"area":null},{"id":"2405.19550","title":"Stress-Testing Capability Elicitation With Password-Locked Models","created":"2024-05-29","cited_by_count":46,"area":null},{"id":"2402.16382","title":"Immunization against harmful fine-tuning attacks","created":"2024-02-26","cited_by_count":35,"area":null},{"id":"2410.04332","title":"Gradient Routing: Masking Gradients to Localize Computation in Neural Networks","created":"2024-10-06","cited_by_count":34,"area":null},{"id":"2406.19354","title":"Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?","created":"2024-06-27","cited_by_count":24,"area":null},{"id":"2508.03153","title":"Estimating Worst-Case Frontier Risks of Open-Weight LLMs","created":"2025-08-05","cited_by_count":19,"area":null},{"id":"2312.14751","title":"Hazards from Increasingly Accessible Fine-Tuning of Downloadable Foundation Models","created":"2023-12-22","cited_by_count":7,"area":null},{"id":"2405.20990","title":"Locking Machine Learning Models into Hardware","created":"2024-05-31","cited_by_count":6,"area":null},{"id":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2304.08315","title":"Thorny Roses: Investigating the Dual Use Dilemma in Natural Language Processing","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2304.10510","title":"Censoring chemical data to mitigate dual use risk","created":"2023-04-20","cited_by_count":3,"area":null},{"id":"2504.06669","title":"NLP Security and Ethics, in the Wild","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2505.04654","title":"A Comparative Analysis of Ethical and Safety Gaps in LLMs using Relative Danger Coefficient","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2605.14605","title":"A Few Steps Further: Why Defenses Against Malicious Finetuning Erode Under Continued Training","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2308.14253","title":"The Promise and Peril of Artificial Intelligence -- Violet Teaming Offers a Balanced Path Forward","created":"2023-08-28","cited_by_count":1,"area":null},{"id":"2502.16701","title":"Beyond Release: Access Considerations for Generative AI Systems","created":"2025-02-23","cited_by_count":1,"area":null},{"id":"2510.16581","title":"Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries","created":"2025-10-18","cited_by_count":1,"area":null},{"id":"2410.23803","title":"Generative AI for Accessible and Inclusive Extended Reality","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2505.06464","title":"Opening the Scope of Openness in AI","created":"2025-05-09","cited_by_count":0,"area":null},{"id":"2605.21683","title":"Investigating Concept Alignment Using Implausible Category Members","created":"2026-05-20","cited_by_count":0,"area":null}],"next_cursor":null}