{"total":118,"rows":[{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202,"area":null},{"id":"2202.07646","title":"Quantifying Memorization Across Neural Language Models","created":"2022-02-15","cited_by_count":763,"area":null},{"id":"2210.01504","title":"Knowledge Unlearning for Mitigating Privacy Risks in Language Models","created":"2022-10-04","cited_by_count":437,"area":"safety"},{"id":"2110.05679","title":"Large Language Models Can Be Strong Differentially Private Learners","created":"2021-10-12","cited_by_count":412,"area":null},{"id":"2110.06500","title":"Differentially Private Fine-tuning of Language Models","created":"2021-10-13","cited_by_count":400,"area":null},{"id":"2204.13650","title":"Unlocking High-Accuracy Differentially Private Image Classification through Scale","created":"2022-04-28","cited_by_count":224,"area":null},{"id":"2310.20150","title":"Unlearn What You Want to Forget: Efficient Unlearning for LLMs","created":"2023-10-31","cited_by_count":215,"area":"safety"},{"id":"2205.12628","title":"Are Large Pre-Trained Language Models Leaking Your Personal Information?","created":"2022-05-25","cited_by_count":200,"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":"2303.00654","title":"How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy","created":"2023-03-01","cited_by_count":153,"area":null},{"id":"2304.11158","title":"Emergent and Predictable Memorization in Large Language Models","created":"2023-04-21","cited_by_count":148,"area":null},{"id":"2210.09929","title":"Differentially Private Diffusion Models","created":"2022-10-18","cited_by_count":119,"area":"diffusion"},{"id":"2303.15715","title":"Foundation Models and Fair Use","created":"2023-03-28","cited_by_count":116,"area":null},{"id":"2210.17546","title":"Preventing Verbatim Memorization in Language Models Gives a False Sense of Privacy","created":"2022-10-31","cited_by_count":100,"area":null},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88,"area":null},{"id":"2201.12328","title":"Toward Training at ImageNet Scale with Differential Privacy","created":"2022-01-28","cited_by_count":87,"area":null},{"id":"2305.15594","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","created":"2023-05-24","cited_by_count":83,"area":null},{"id":"2403.01749","title":"Differentially Private Synthetic Data via Foundation Model APIs 2: Text","created":"2024-03-04","cited_by_count":76,"area":"synth"},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68,"area":null},{"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":"2305.15560","title":"Differentially Private Synthetic Data via Foundation Model APIs 1: Images","created":"2023-05-24","cited_by_count":65,"area":null},{"id":"2111.06578","title":"Differential privacy and robust statistics in high dimensions","created":"2021-11-12","cited_by_count":64,"area":null},{"id":"2207.01193","title":"A Customized Text Sanitization Mechanism with Differential Privacy","created":"2022-07-04","cited_by_count":52,"area":null},{"id":"2210.03403","title":"TAN Without a Burn: Scaling Laws of DP-SGD","created":"2022-10-07","cited_by_count":52,"area":null},{"id":"2212.01539","title":"Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping","created":"2022-12-03","cited_by_count":52,"area":null},{"id":"2406.10209","title":"Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs","created":"2024-06-14","cited_by_count":50,"area":null},{"id":"2407.14937","title":"Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)","created":"2024-07-20","cited_by_count":46,"area":"safety"},{"id":"2111.15521","title":"Node-Level Differentially Private Graph Neural Networks","created":"2021-11-23","cited_by_count":43,"area":null},{"id":"2305.06212","title":"Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services","created":"2023-05-10","cited_by_count":43,"area":null},{"id":"2405.03097","title":"To Each (Textual Sequence) Its Own: Improving Memorized-Data Unlearning in Large Language Models","created":"2024-05-06","cited_by_count":43,"area":"safety"},{"id":"2205.02973","title":"Large Scale Transfer Learning for Differentially Private Image Classification","created":"2022-05-06","cited_by_count":41,"area":null},{"id":"2312.17493","title":"Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning","created":"2023-12-29","cited_by_count":41,"area":null},{"id":"2302.03098","title":"One-shot Empirical Privacy Estimation for Federated Learning","created":"2023-02-06","cited_by_count":36,"area":null},{"id":"2402.13659","title":"Privacy-Preserving Instructions for Aligning Large Language Models","created":"2024-02-21","cited_by_count":35,"area":"alignment"},{"id":"2204.07667","title":"Just Fine-tune Twice: Selective Differential Privacy for Large Language Models","created":"2022-04-15","cited_by_count":32,"area":null},{"id":"2411.10512","title":"On the Privacy Risk of In-context Learning","created":"2024-11-15","cited_by_count":32,"area":"safety"},{"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":"2406.02958","title":"PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs","created":"2024-06-05","cited_by_count":29,"area":null},{"id":"2209.15259","title":"On the Impossible Safety of Large AI Models","created":"2022-09-30","cited_by_count":28,"area":null},{"id":"2305.12707","title":"Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage","created":"2023-05-22","cited_by_count":28,"area":null},{"id":"2405.10989","title":"Learnable Privacy Neurons Localization in Language Models","created":"2024-05-16","cited_by_count":27,"area":null},{"id":"2310.14369","title":"MoPe: Model Perturbation-based Privacy Attacks on Language Models","created":"2023-10-22","cited_by_count":25,"area":null},{"id":"2406.14322","title":"Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning","created":"2024-06-20","cited_by_count":24,"area":null},{"id":"2211.10844","title":"Learning to Generate Image Embeddings with User-level Differential Privacy","created":"2022-11-20","cited_by_count":23,"area":null},{"id":"2305.13865","title":"Selective Pre-training for Private Fine-tuning","created":"2023-05-23","cited_by_count":23,"area":null},{"id":"2406.05392","title":"Deconstructing The Ethics of Large Language Models from Long-standing Issues to New-emerging Dilemmas: A Survey","created":"2024-06-08","cited_by_count":23,"area":null},{"id":"2503.06808","title":"Privacy Auditing of Large Language Models","created":"2025-03-09","cited_by_count":23,"area":"safety"},{"id":"2403.17673","title":"How Private are DP-SGD Implementations?","created":"2024-03-26","cited_by_count":22,"area":null},{"id":"2206.02617","title":"Individual Privacy Accounting for Differentially Private Stochastic Gradient Descent","created":"2022-06-06","cited_by_count":20,"area":null},{"id":"2301.09112","title":"Differentially Private Natural Language Models: Recent Advances and Future Directions","created":"2023-01-22","cited_by_count":20,"area":null},{"id":"2304.09762","title":"Practical Differentially Private and Byzantine-resilient Federated Learning","created":"2023-04-15","cited_by_count":18,"area":null},{"id":"2302.02936","title":"Private GANs, Revisited","created":"2023-02-06","cited_by_count":17,"area":null},{"id":"2306.08842","title":"ViP: A Differentially Private Foundation Model for Computer Vision","created":"2023-06-15","cited_by_count":17,"area":null},{"id":"2207.08988","title":"Training Large-Vocabulary Neural Language Models by Private Federated Learning for Resource-Constrained Devices","created":"2022-07-18","cited_by_count":16,"area":null},{"id":"2308.10888","title":"Unlocking Accuracy and Fairness in Differentially Private Image Classification","created":"2023-08-21","cited_by_count":16,"area":null},{"id":"2411.04205","title":"Scalable DP-SGD: Shuffling vs. Poisson Subsampling","created":"2024-11-06","cited_by_count":16,"area":null},{"id":"2412.16802","title":"Balls-and-Bins Sampling for DP-SGD","created":"2024-12-21","cited_by_count":14,"area":null},{"id":"2205.01863","title":"Provably Confidential Language Modelling","created":"2022-05-04","cited_by_count":13,"area":null},{"id":"2206.01838","title":"Differentially Private Model Compression","created":"2022-06-03","cited_by_count":13,"area":null},{"id":"2406.09325","title":"REVS: Unlearning Sensitive Information in Language Models via Rank Editing in the Vocabulary Space","created":"2024-06-13","cited_by_count":13,"area":"safety"},{"id":"2212.10520","title":"Privacy-Preserving Domain Adaptation of Semantic Parsers","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2403.05681","title":"DP-TabICL: In-Context Learning with Differentially Private Tabular Data","created":"2024-03-08","cited_by_count":11,"area":null},{"id":"2211.02956","title":"Privacy-Preserving Models for Legal Natural Language Processing","created":"2022-11-05","cited_by_count":10,"area":null},{"id":"2506.10424","title":"SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks","created":"2025-06-12","cited_by_count":10,"area":"safety"},{"id":"2306.15742","title":"Differentially Private Video Activity Recognition","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2410.19406","title":"An Auditing Test To Detect Behavioral Shift in Language Models","created":"2024-10-25","cited_by_count":9,"area":null},{"id":"2402.16515","title":"LLM-based Privacy Data Augmentation Guided by Knowledge Distillation with a Distribution Tutor for Medical Text Classification","created":"2024-02-26","cited_by_count":8,"area":"distill"},{"id":"2503.06040","title":"Mitigating Memorization in LLMs using Activation Steering","created":"2025-03-08","cited_by_count":8,"area":"mechinterp"},{"id":"2112.14430","title":"DP-FP: Differentially Private Forward Propagation for Large Models","created":"2021-12-29","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":"2211.13403","title":"Differentially Private Image Classification from Features","created":"2022-11-24","cited_by_count":7,"area":null},{"id":"2412.06619","title":"Copyright-Protected Language Generation via Adaptive Model Fusion","created":"2024-12-09","cited_by_count":7,"area":null},{"id":"2211.11896","title":"Private Ad Modeling with DP-SGD","created":"2022-11-21","cited_by_count":6,"area":null},{"id":"2403.04124","title":"Privacy-preserving Fine-tuning of Large Language Models through Flatness","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2301.00738","title":"Training Differentially Private Graph Neural Networks with Random Walk Sampling","created":"2023-01-02","cited_by_count":5,"area":null},{"id":"2306.04803","title":"Privately generating tabular data using language models","created":"2023-06-07","cited_by_count":5,"area":null},{"id":"2405.18194","title":"Delving into Differentially Private Transformer","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2502.06597","title":"Continual Release Moment Estimation with Differential Privacy","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2208.12392","title":"DiVa: An Accelerator for Differentially Private Machine Learning","created":"2022-08-26","cited_by_count":4,"area":null},{"id":"2407.20105","title":"Strong Copyright Protection for Language Models via Adaptive Model Fusion","created":"2024-07-29","cited_by_count":4,"area":null},{"id":"2601.10237","title":"Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2503.07697","title":"PoisonedParrot: Subtle Data Poisoning Attacks to Elicit Copyright-Infringing Content from Large Language Models","created":"2025-03-10","cited_by_count":3,"area":"safety"},{"id":"2503.12314","title":"Empirical Privacy Variance","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2604.07238","title":"On the Price of Privacy for Language Identification and Generation","created":"2026-04-08","cited_by_count":3,"area":null},{"id":"2305.01550","title":"Mitigating Approximate Memorization in Language Models via Dissimilarity Learned Policy","created":"2023-05-02","cited_by_count":2,"area":null},{"id":"2305.17633","title":"DPFormer: Learning Differentially Private Transformer on Long-Tailed Data","created":"2023-05-28","cited_by_count":2,"area":null},{"id":"2405.08026","title":"ExplainableDetector: Exploring Transformer-based Language Modeling Approach for SMS Spam Detection with Explainability Analysis","created":"2024-05-12","cited_by_count":2,"area":null},{"id":"2409.13953","title":"Training Large ASR Encoders with Differential Privacy","created":"2024-09-21","cited_by_count":2,"area":null},{"id":"2409.15907","title":"Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injection","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2410.18749","title":"Does Differential Privacy Impact Bias in Pretrained NLP Models?","created":"2024-10-24","cited_by_count":2,"area":null},{"id":"2410.23472","title":"Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems","created":"2024-10-30","cited_by_count":2,"area":null},{"id":"2502.05159","title":"A Lightweight Method to Disrupt Memorized Sequences in LLM","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2505.13171","title":"Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks","created":"2025-05-19","cited_by_count":2,"area":null},{"id":"2211.04686","title":"Directional Privacy for Deep Learning","created":"2022-11-09","cited_by_count":1,"area":null},{"id":"2307.07477","title":"Population Expansion for Training Language Models with Private Federated Learning","created":"2023-07-14","cited_by_count":1,"area":null},{"id":"2312.13389","title":"Enhancing Trade-offs in Privacy, Utility, and Computational Efficiency through MUltistage Sampling Technique (MUST)","created":"2023-12-20","cited_by_count":1,"area":null},{"id":"2404.08847","title":"LazyDP: Co-Designing Algorithm-Software for Scalable Training of Differentially Private Recommendation Models","created":"2024-04-12","cited_by_count":1,"area":null}],"next_cursor":"100"}