{"total":90,"rows":[{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"area":null},{"id":"2209.02299","title":"A Survey of Machine Unlearning","created":"2022-09-06","cited_by_count":312,"area":"safety"},{"id":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2109.13398","title":"Unrolling SGD: Understanding Factors Influencing Machine Unlearning","created":"2021-09-27","cited_by_count":279,"area":"safety"},{"id":"2108.11577","title":"Machine Unlearning of Features and Labels","created":"2021-08-26","cited_by_count":229,"area":"safety"},{"id":"2406.01171","title":"Two Tales of Persona in LLMs: A Survey of Role-Playing and Personalization","created":"2024-06-03","cited_by_count":208,"area":null},{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195,"area":null},{"id":"2402.00888","title":"Security and Privacy Challenges of Large Language Models: A Survey","created":"2024-01-30","cited_by_count":186,"area":"safety"},{"id":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175,"area":"safety"},{"id":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156,"area":null},{"id":"2201.04845","title":"Reconstructing Training Data with Informed Adversaries","created":"2022-01-13","cited_by_count":148,"area":null},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"id":"2204.00032","title":"Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets","created":"2022-03-31","cited_by_count":101,"area":null},{"id":"2105.00164","title":"Hidden Backdoors in Human-Centric Language Models","created":"2021-05-01","cited_by_count":90,"area":"safety"},{"id":"2201.06820","title":"Recommendation Unlearning","created":"2022-01-18","cited_by_count":80,"area":null},{"id":"2203.07618","title":"Do Language Models Plagiarize?","created":"2022-03-15","cited_by_count":73,"area":null},{"id":"2205.08514","title":"Recovering Private Text in Federated Learning of Language Models","created":"2022-05-17","cited_by_count":70,"area":null},{"id":"2305.10036","title":"Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark","created":"2023-05-17","cited_by_count":67,"area":"safety"},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2402.01822","title":"Building Guardrails for Large Language Models","created":"2024-02-02","cited_by_count":65,"area":"safety"},{"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":"2201.12675","title":"Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models","created":"2022-01-29","cited_by_count":53,"area":null},{"id":"2212.10986","title":"SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning","created":"2022-12-21","cited_by_count":51,"area":null},{"id":"2401.04536","title":"Evaluating Language Model Agency through Negotiations","created":"2024-01-09","cited_by_count":48,"area":null},{"id":"2205.12506","title":"Memorization in NLP Fine-tuning Methods","created":"2022-05-25","cited_by_count":45,"area":null},{"id":"2212.10717","title":"Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks","created":"2022-12-21","cited_by_count":43,"area":"safety"},{"id":"2210.10750","title":"Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries","created":"2022-10-19","cited_by_count":40,"area":"safety"},{"id":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"area":"safety"},{"id":"2307.04401","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","created":"2023-07-10","cited_by_count":36,"area":null},{"id":"2106.11384","title":"Membership Inference on Word Embedding and Beyond","created":"2021-06-21","cited_by_count":35,"area":"safety"},{"id":"2405.07406","title":"Machine Unlearning: A Comprehensive Survey","created":"2024-05-13","cited_by_count":35,"area":"safety"},{"id":"2206.05199","title":"Bayesian Estimation of Differential Privacy","created":"2022-06-10","cited_by_count":33,"area":"safety"},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2310.01424","title":"Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey","created":"2023-09-27","cited_by_count":30,"area":null},{"id":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30,"area":null},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"id":"2502.18509","title":"Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents","created":"2025-02-22","cited_by_count":26,"area":"agents"},{"id":"2202.03460","title":"Deletion Inference, Reconstruction, and Compliance in Machine (Un)Learning","created":"2022-02-07","cited_by_count":24,"area":"safety"},{"id":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2306.03558","title":"Machine Unlearning: A Survey","created":"2023-06-06","cited_by_count":19,"area":"safety"},{"id":"2111.04424","title":"A Framework for Deprecating Datasets: Standardizing Documentation, Identification, and Communication","created":"2021-10-18","cited_by_count":18,"area":null},{"id":"2308.15727","title":"Quantifying and Analyzing Entity-level Memorization in Large Language Models","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2502.14921","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","created":"2025-02-19","cited_by_count":18,"area":"synth"},{"id":"2209.08615","title":"Membership Inference Attacks and Generalization: A Causal Perspective","created":"2022-09-18","cited_by_count":17,"area":"safety"},{"id":"2301.10412","title":"BDMMT: Backdoor Sample Detection for Language Models through Model Mutation Testing","created":"2023-01-25","cited_by_count":16,"area":"safety"},{"id":"2501.18532","title":"Differentially Private Steering for Large Language Model Alignment","created":"2025-01-30","cited_by_count":15,"area":"alignment"},{"id":"2312.05114","title":"The Inadequacy of Similarity-based Privacy Metrics: Privacy Attacks against \"Truly Anonymous\" Synthetic Datasets","created":"2023-12-08","cited_by_count":14,"area":null},{"id":"2412.16504","title":"Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions","created":"2024-12-21","cited_by_count":14,"area":"safety"},{"id":"2406.11715","title":"Measuring memorization in RLHF for code completion","created":"2024-06-17","cited_by_count":13,"area":"alignment"},{"id":"2205.10228","title":"You Don't Know My Favorite Color: Preventing Dialogue Representations from Revealing Speakers' Private Personas","created":"2022-04-26","cited_by_count":11,"area":null},{"id":"2306.15744","title":"Ticketed Learning-Unlearning Schemes","created":"2023-06-27","cited_by_count":11,"area":"safety"},{"id":"2311.05863","title":"Watermarking Vision-Language Pre-trained Models for Multi-modal Embedding as a Service","created":"2023-11-10","cited_by_count":11,"area":"mllm"},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2206.04591","title":"Privacy Leakage in Text Classification: A Data Extraction Approach","created":"2022-06-09","cited_by_count":10,"area":null},{"id":"2305.05973","title":"Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models","created":"2023-05-10","cited_by_count":10,"area":null},{"id":"2405.15523","title":"The Mosaic Memory of Large Language Models","created":"2024-05-24","cited_by_count":10,"area":null},{"id":"2202.04856","title":"PPA: Preference Profiling Attack Against Federated Learning","created":"2022-02-10","cited_by_count":9,"area":null},{"id":"2308.13904","title":"LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors","created":"2023-08-26","cited_by_count":9,"area":"safety"},{"id":"2310.08565","title":"Security Considerations in AI-Robotics: A Survey of Current Methods, Challenges, and Opportunities","created":"2023-10-12","cited_by_count":9,"area":null},{"id":"2402.02103","title":"D\\'ej\\`a Vu Memorization in Vision-Language Models","created":"2024-02-03","cited_by_count":9,"area":"mllm"},{"id":"2405.19211","title":"Gone but Not Forgotten: Improved Benchmarks for Machine Unlearning","created":"2024-05-29","cited_by_count":9,"area":"safety"},{"id":"2205.06369","title":"How to Combine Membership-Inference Attacks on Multiple Updated Models","created":"2022-05-12","cited_by_count":8,"area":"safety"},{"id":"2101.05405","title":"Training Data Leakage Analysis in Language Models","created":"2021-01-14","cited_by_count":7,"area":null},{"id":"2207.10802","title":"Combing for Credentials: Active Pattern Extraction from Smart Reply","created":"2022-07-14","cited_by_count":7,"area":null},{"id":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2210.16023","title":"LegoNet: A Fast and Exact Unlearning Architecture","created":"2022-10-28","cited_by_count":6,"area":"safety"},{"id":"2306.00133","title":"A Note On Interpreting Canary Exposure","created":"2023-05-31","cited_by_count":6,"area":null},{"id":"2306.13789","title":"Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models","created":"2023-06-23","cited_by_count":6,"area":null},{"id":"2307.15960","title":"Recommendation Unlearning via Matrix Correction","created":"2023-07-29","cited_by_count":6,"area":null},{"id":"2506.17353","title":"Differentiation-Based Extraction of Proprietary Data from Fine-Tuned LLMs","created":"2025-06-20","cited_by_count":6,"area":"alignment"},{"id":"2106.15335","title":"Privacy Budget Scheduling","created":"2021-06-29","cited_by_count":4,"area":null},{"id":"2405.09805","title":"SecureLLM: Using Compositionality to Build Provably Secure Language Models for Private, Sensitive, and Secret Data","created":"2024-05-16","cited_by_count":4,"area":null},{"id":"2406.14549","title":"Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models","created":"2024-06-20","cited_by_count":4,"area":null},{"id":"2110.03369","title":"The Connection between Out-of-Distribution Generalization and Privacy of ML Models","created":"2021-10-07","cited_by_count":3,"area":null},{"id":"2312.14480","title":"MetaAID 2.5: A Secure Framework for Developing Metaverse Applications via Large Language Models","created":"2023-12-22","cited_by_count":3,"area":null},{"id":"2406.00839","title":"FOCUS: Forging Originality through Contrastive Use in Self-Plagiarism for Language Models","created":"2024-06-02","cited_by_count":3,"area":null},{"id":"2211.02245","title":"Unintended Memorization and Timing Attacks in Named Entity Recognition Models","created":"2022-11-04","cited_by_count":2,"area":"safety"},{"id":"2309.11022","title":"Information Leakage from Data Updates in Machine Learning Models","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2402.07334","title":"Differentially Private Training of Mixture of Experts Models","created":"2024-02-11","cited_by_count":2,"area":"moe"},{"id":"2504.06398","title":"Sharpness-Aware Parameter Selection for Machine Unlearning","created":"2025-04-08","cited_by_count":2,"area":"safety"},{"id":"2509.12152","title":"Beyond PII: How Users Attempt to Estimate and Mitigate Implicit LLM Inference","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2204.10958","title":"Towards Privacy-Preserving Neural Architecture Search","created":"2022-04-22","cited_by_count":1,"area":null},{"id":"2212.03749","title":"Memorization of Named Entities in Fine-tuned BERT Models","created":"2022-12-07","cited_by_count":1,"area":null},{"id":"2212.08619","title":"Planting and Mitigating Memorized Content in Predictive-Text Language Models","created":"2022-12-16","cited_by_count":1,"area":null},{"id":"2310.19459","title":"Security Challenges for Cloud or Fog Computing-Based AI Applications","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2507.23291","title":"Evaluating the Dynamics of Membership Privacy in Deep Learning","created":"2025-07-31","cited_by_count":1,"area":"safety"},{"id":"2602.16596","title":"Sequential Membership Inference Attacks","created":"2026-02-18","cited_by_count":1,"area":"safety"},{"id":"2606.28479","title":"Decomposing Memorization Reduction in Privacy-Preserving Fine-Tuning of SLMs for CSIRTs","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2212.11121","title":"Religion and Spirituality on Social Media in the Aftermath of the Global Pandemic","created":"2022-12-11","cited_by_count":0,"area":null},{"id":"2602.17418","title":"A Privacy by Design Framework for Large Language Model-Based Applications for Children","created":"2026-02-19","cited_by_count":0,"area":null}],"next_cursor":null}