{"total":404,"rows":[{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387,"area":null},{"id":"2312.02003","title":"A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly","created":"2023-12-04","cited_by_count":387,"area":null},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"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":"2112.12938","title":"Counterfactual Memorization in Neural Language Models","created":"2021-12-24","cited_by_count":156,"area":null},{"id":"2206.10469","title":"The Privacy Onion Effect: Memorization is Relative","created":"2022-06-21","cited_by_count":136,"area":null},{"id":"2305.08846","title":"Privacy Auditing with One (1) Training Run","created":"2023-05-15","cited_by_count":123,"area":null},{"id":"2206.00240","title":"Privacy for Free: How does Dataset Condensation Help Privacy?","created":"2022-06-01","cited_by_count":120,"area":null},{"id":"2207.00099","title":"Measuring Forgetting of Memorized Training Examples","created":"2022-06-30","cited_by_count":118,"area":null},{"id":"2404.02936","title":"Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models","created":"2024-04-03","cited_by_count":103,"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":"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":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2402.09910","title":"DE-COP: Detecting Copyrighted Content in Language Models Training Data","created":"2024-02-15","cited_by_count":74,"area":null},{"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":"2312.03724","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","created":"2023-11-27","cited_by_count":57,"area":null},{"id":"2409.14781","title":"Pretraining Data Detection for Large Language Models: A Divergence-based Calibration Method","created":"2024-09-23","cited_by_count":55,"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":"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":"2302.09923","title":"Prompt Stealing Attacks Against Text-to-Image Generation Models","created":"2023-02-20","cited_by_count":51,"area":null},{"id":"2205.12506","title":"Memorization in NLP Fine-tuning Methods","created":"2022-05-25","cited_by_count":45,"area":null},{"id":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2408.12787","title":"LLM-PBE: Assessing Data Privacy in Large Language Models","created":"2024-08-23","cited_by_count":41,"area":null},{"id":"2309.05610","title":"Privacy Side Channels in Machine Learning Systems","created":"2023-09-11","cited_by_count":40,"area":null},{"id":"2402.09363","title":"Copyright Traps for Large Language Models","created":"2024-02-14","cited_by_count":37,"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":"2310.09266","title":"User Inference Attacks on Large Language Models","created":"2023-10-13","cited_by_count":36,"area":null},{"id":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36,"area":null},{"id":"2404.06209","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models","created":"2024-04-09","cited_by_count":36,"area":null},{"id":"2404.17399","title":"Evaluations of Machine Learning Privacy Defenses are Misleading","created":"2024-04-26","cited_by_count":36,"area":null},{"id":"2202.07623","title":"Defending against Reconstruction Attacks with R\\'enyi Differential Privacy","created":"2022-02-15","cited_by_count":32,"area":null},{"id":"2403.00871","title":"Teach LLMs to Phish: Stealing Private Information from Language Models","created":"2024-03-01","cited_by_count":32,"area":null},{"id":"2208.12348","title":"SNAP: Efficient Extraction of Private Properties with Poisoning","created":"2022-08-25","cited_by_count":31,"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":"2402.02823","title":"Evading Data Contamination Detection for Language Models is (too) Easy","created":"2024-02-05","cited_by_count":30,"area":null},{"id":"2404.01231","title":"Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models","created":"2024-04-01","cited_by_count":30,"area":null},{"id":"2406.14644","title":"Unveiling the Spectrum of Data Contamination in Language Models: A Survey from Detection to Remediation","created":"2024-06-20","cited_by_count":30,"area":null},{"id":"2410.22235","title":"Auditing $f$-Differential Privacy in One Run","created":"2024-10-29","cited_by_count":30,"area":null},{"id":"2312.14334","title":"DP-AdamBC: Your DP-Adam Is Actually DP-SGD (Unless You Apply Bias Correction)","created":"2023-12-21","cited_by_count":28,"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":"2406.01333","title":"Probing Language Models for Pre-training Data Detection","created":"2024-06-03","cited_by_count":25,"area":null},{"id":"2301.10053","title":"A Linear Reconstruction Approach for Attribute Inference Attacks against Synthetic Data","created":"2023-01-24","cited_by_count":24,"area":null},{"id":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2205.08443","title":"On the (In)security of Peer-to-Peer Decentralized Machine Learning","created":"2022-05-17","cited_by_count":23,"area":null},{"id":"2205.13741","title":"Generating multivariate time series with COmmon Source CoordInated GAN (COSCI-GAN)","created":"2022-05-27","cited_by_count":23,"area":null},{"id":"2209.14987","title":"No Free Lunch in \"Privacy for Free: How does Dataset Condensation Help Privacy\"","created":"2022-09-29","cited_by_count":23,"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":"2306.16064","title":"Federated Generative Learning with Foundation Models","created":"2023-06-28","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":"2504.12459","title":"On Linear Representations and Pretraining Data Frequency in Language Models","created":"2025-04-16","cited_by_count":23,"area":null},{"id":"2303.17046","title":"Have it your way: Individualized Privacy Assignment for DP-SGD","created":"2023-03-29","cited_by_count":21,"area":null},{"id":"2310.07152","title":"No Privacy Left Outside: On the (In-)Security of TEE-Shielded DNN Partition for On-Device ML","created":"2023-10-11","cited_by_count":21,"area":null},{"id":"2405.11525","title":"Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors","created":"2024-05-19","cited_by_count":21,"area":null},{"id":"2405.14106","title":"Nearly Tight Black-Box Auditing of Differentially Private Machine Learning","created":"2024-05-23","cited_by_count":21,"area":null},{"id":"2503.17514","title":"Language Models May Verbatim Complete Text They Were Not Explicitly Trained On","created":"2025-03-21","cited_by_count":21,"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":"2305.18447","title":"Unleashing the Power of Randomization in Auditing Differentially Private ML","created":"2023-05-29","cited_by_count":20,"area":null},{"id":"2307.16273","title":"zkDL: Efficient Zero-Knowledge Proofs of Deep Learning Training","created":"2023-07-30","cited_by_count":20,"area":null},{"id":"2309.17310","title":"Leave-one-out Distinguishability in Machine Learning","created":"2023-09-29","cited_by_count":20,"area":null},{"id":"2409.03363","title":"Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding","created":"2024-09-05","cited_by_count":20,"area":null},{"id":"2207.13766","title":"Label-Only Membership Inference Attack against Node-Level Graph Neural Networks","created":"2022-07-27","cited_by_count":19,"area":null},{"id":"2209.07341","title":"Does CLIP Know My Face?","created":"2022-09-15","cited_by_count":19,"area":null},{"id":"2308.15709","title":"Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation","created":"2023-08-30","cited_by_count":19,"area":null},{"id":"2403.06644","title":"Elephants Never Forget: Testing Language Models for Memorization of Tabular Data","created":"2024-03-11","cited_by_count":19,"area":null},{"id":"2405.14457","title":"Tighter Privacy Auditing of DP-SGD in the Hidden State Threat Model","created":"2024-05-23","cited_by_count":18,"area":null},{"id":"2210.13662","title":"Analyzing Privacy Leakage in Machine Learning via Multiple Hypothesis Testing: A Lesson From Fano","created":"2022-10-24","cited_by_count":17,"area":null},{"id":"2312.10108","title":"Privacy-Aware Document Visual Question Answering","created":"2023-12-15","cited_by_count":17,"area":null},{"id":"2405.19524","title":"AI Risk Management Should Incorporate Both Safety and Security","created":"2024-05-29","cited_by_count":17,"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":"2311.15792","title":"Rethinking Privacy in Machine Learning Pipelines from an Information Flow Control Perspective","created":"2023-11-27","cited_by_count":16,"area":null},{"id":"2402.02987","title":"Reconstruct Your Previous Conversations! Comprehensively Investigating Privacy Leakage Risks in Conversations with GPT Models","created":"2024-02-05","cited_by_count":16,"area":null},{"id":"2407.15100","title":"A General Framework for Data-Use Auditing of ML Models","created":"2024-07-21","cited_by_count":16,"area":null},{"id":"2208.08270","title":"On the Privacy Effect of Data Enhancement via the Lens of Memorization","created":"2022-08-17","cited_by_count":15,"area":null},{"id":"2208.10134","title":"Machine Learning with Confidential Computing: A Systematization of Knowledge","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2307.03928","title":"Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy","created":"2023-07-08","cited_by_count":15,"area":null},{"id":"2406.03880","title":"Memorization in deep learning: A survey","created":"2024-06-06","cited_by_count":15,"area":null},{"id":"2502.00678","title":"How Contaminated Is Your Benchmark? Quantifying Dataset Leakage in Large Language Models with Kernel Divergence","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2502.02260","title":"Position: Adversarial ML for LLMs Is Not Making Any Progress","created":"2025-02-04","cited_by_count":15,"area":null},{"id":"2503.05954","title":"A Survey on Deep Learning Approaches for Tabular Data Generation: Utility, Alignment, Fidelity, Privacy, Diversity, and Beyond","created":"2025-03-07","cited_by_count":15,"area":null},{"id":"2302.01428","title":"Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation","created":"2023-02-02","cited_by_count":14,"area":null},{"id":"2306.01181","title":"TMI! Finetuned Models Leak Private Information from their Pretraining Data","created":"2023-06-01","cited_by_count":14,"area":null},{"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":"2402.09327","title":"Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization","created":"2024-02-14","cited_by_count":14,"area":null},{"id":"2411.10242","title":"Measuring Non-Adversarial Reproduction of Training Data in Large Language Models","created":"2024-11-15","cited_by_count":14,"area":null},{"id":"2311.07682","title":"Fuse to Forget: Bias Reduction and Selective Memorization through Model Fusion","created":"2023-11-13","cited_by_count":13,"area":null},{"id":"2402.01862","title":"Parametric Feature Transfer: One-shot Federated Learning with Foundation Models","created":"2024-02-02","cited_by_count":13,"area":null},{"id":"2405.03636","title":"The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape","created":"2024-05-06","cited_by_count":13,"area":null},{"id":"2406.14318","title":"The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2407.16607","title":"Data Mixture Inference: What do BPE Tokenizers Reveal about their Training Data?","created":"2024-07-23","cited_by_count":13,"area":null},{"id":"2302.01190","title":"On the Efficacy of Differentially Private Few-shot Image Classification","created":"2023-02-02","cited_by_count":12,"area":null},{"id":"2402.09540","title":"Why Does Differential Privacy with Large Epsilon Defend Against Practical Membership Inference Attacks?","created":"2024-02-14","cited_by_count":12,"area":null},{"id":"2404.00699","title":"A Comprehensive Survey of Contamination Detection Methods in Large Language Models","created":"2024-03-31","cited_by_count":12,"area":null},{"id":"2502.12976","title":"Does Training with Synthetic Data Truly Protect Privacy?","created":"2025-02-18","cited_by_count":12,"area":null},{"id":"2503.14043","title":"Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2208.13893","title":"Data Isotopes for Data Provenance in DNNs","created":"2022-08-29","cited_by_count":11,"area":null},{"id":"2306.00127","title":"Surrogate Model Extension (SME): A Fast and Accurate Weight Update Attack on Federated Learning","created":"2023-05-31","cited_by_count":11,"area":null},{"id":"2402.19232","title":"Trained Random Forests Completely Reveal your Dataset","created":"2024-02-29","cited_by_count":11,"area":null},{"id":"2407.21248","title":"Adaptive Pre-training Data Detection for Large Language Models via Surprising Tokens","created":"2024-07-30","cited_by_count":11,"area":null},{"id":"2410.06186","title":"The Last Iterate Advantage: Empirical Auditing and Principled Heuristic Analysis of Differentially Private SGD","created":"2024-10-08","cited_by_count":11,"area":null},{"id":"2204.09606","title":"Detecting Unintended Memorization in Language-Model-Fused ASR","created":"2022-04-20","cited_by_count":10,"area":null}],"next_cursor":"100"}