{"total":116,"rows":[{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"area":"safety"},{"id":"2308.05374","title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","created":"2023-08-10","cited_by_count":401,"area":null},{"id":"2305.15717","title":"The False Promise of Imitating Proprietary LLMs","created":"2023-05-25","cited_by_count":263,"area":"synth"},{"id":"2406.06443","title":"LLM Dataset Inference: Did you train on my dataset?","created":"2024-06-10","cited_by_count":110,"area":"safety"},{"id":"2404.15146","title":"Rethinking LLM Memorization through the Lens of Adversarial Compression","created":"2024-04-23","cited_by_count":94,"area":"lr"},{"id":"2206.08451","title":"I Know What You Trained Last Summer: A Survey on Stealing Machine Learning Models and Defences","created":"2022-06-16","cited_by_count":75,"area":null},{"id":"2409.19798","title":"Membership Inference Attacks Cannot Prove that a Model Was Trained On Your Data","created":"2024-09-29","cited_by_count":50,"area":"safety"},{"id":"2112.03476","title":"Defending against Model Stealing via Verifying Embedded External Features","created":"2021-12-07","cited_by_count":46,"area":null},{"id":"2112.05588","title":"Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models","created":"2021-12-10","cited_by_count":46,"area":"safety"},{"id":"2109.06024","title":"Formalizing and Estimating Distribution Inference Risks","created":"2021-09-13","cited_by_count":43,"area":null},{"id":"2405.04825","title":"Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution","created":"2024-05-08","cited_by_count":40,"area":"safety"},{"id":"2310.18362","title":"SoK: Memorization in General-Purpose Large Language Models","created":"2023-10-24","cited_by_count":37,"area":null},{"id":"2209.09024","title":"Dataset Inference for Self-Supervised Models","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2105.00623","title":"Black-Box Dissector: Towards Erasing-based Hard-Label Model Stealing Attack","created":"2021-05-03","cited_by_count":25,"area":null},{"id":"2411.00154","title":"Scaling Up Membership Inference: When and How Attacks Succeed on Large Language Models","created":"2024-10-31","cited_by_count":24,"area":"safety"},{"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":"2205.07890","title":"On the Difficulty of Defending Self-Supervised Learning against Model Extraction","created":"2022-05-16","cited_by_count":22,"area":null},{"id":"2201.09243","title":"Increasing the Cost of Model Extraction with Calibrated Proof of Work","created":"2022-01-23","cited_by_count":21,"area":null},{"id":"2208.02820","title":"MOVE: Effective and Harmless Ownership Verification via Embedded External Features","created":"2022-08-04","cited_by_count":21,"area":null},{"id":"2406.01983","title":"RKLD: Reverse KL-Divergence-based Knowledge Distillation for Unlearning Personal Information in Large Language Models","created":"2024-06-04","cited_by_count":21,"area":"safety"},{"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":"2410.10437","title":"Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models","created":"2024-10-14","cited_by_count":20,"area":"diffusion"},{"id":"2211.07138","title":"Watermarking in Secure Federated Learning: A Verification Framework Based on Client-Side Backdooring","created":"2022-11-14","cited_by_count":17,"area":null},{"id":"2304.06607","title":"False Claims against Model Ownership Resolution","created":"2023-04-13","cited_by_count":17,"area":null},{"id":"2411.12858","title":"CDI: Copyrighted Data Identification in Diffusion Models","created":"2024-11-19","cited_by_count":17,"area":"diffusion"},{"id":"2304.08566","title":"GrOVe: Ownership Verification of Graph Neural Networks using Embeddings","created":"2023-04-17","cited_by_count":16,"area":null},{"id":"2410.03537","title":"Ward: Provable RAG Dataset Inference via LLM Watermarks","created":"2024-10-04","cited_by_count":16,"area":"safety"},{"id":"2202.12232","title":"Bounding Membership Inference","created":"2022-02-24","cited_by_count":15,"area":"safety"},{"id":"2410.16618","title":"SoK: Dataset Copyright Auditing in Machine Learning Systems","created":"2024-10-22","cited_by_count":15,"area":null},{"id":"2502.00706","title":"Model Provenance Testing for Large Language Models","created":"2025-02-02","cited_by_count":15,"area":null},{"id":"2502.02514","title":"Privacy Attacks on Image AutoRegressive Models","created":"2025-02-04","cited_by_count":15,"area":"diffusion"},{"id":"2403.02116","title":"Inf2Guard: An Information-Theoretic Framework for Learning Privacy-Preserving Representations against Inference Attacks","created":"2024-03-04","cited_by_count":13,"area":"safety"},{"id":"2202.12506","title":"On the Effectiveness of Dataset Watermarking in Adversarial Settings","created":"2022-02-25","cited_by_count":12,"area":null},{"id":"2207.01991","title":"Conflicting Interactions Among Protection Mechanisms for Machine Learning Models","created":"2022-07-05","cited_by_count":12,"area":null},{"id":"2502.10673","title":"Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs","created":"2025-02-15","cited_by_count":12,"area":"rag"},{"id":"2208.13893","title":"Data Isotopes for Data Provenance in DNNs","created":"2022-08-29","cited_by_count":11,"area":null},{"id":"2309.03081","title":"ORL-AUDITOR: Dataset Auditing in Offline Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":11,"area":"offlinerl"},{"id":"2510.19796","title":"Blackbox Model Provenance via Palimpsestic Membership Inference","created":"2025-10-22","cited_by_count":11,"area":"safety"},{"id":"2109.10870","title":"SoK: Machine Learning Governance","created":"2021-09-20","cited_by_count":10,"area":null},{"id":"2501.15509","title":"FIT-Print: Towards False-claim-resistant Model Ownership Verification via Targeted Fingerprint","created":"2025-01-26","cited_by_count":10,"area":null},{"id":"2210.13631","title":"On the Robustness of Dataset Inference","created":"2022-10-24","cited_by_count":8,"area":null},{"id":"2310.08571","title":"Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2410.09101","title":"Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning","created":"2024-10-09","cited_by_count":8,"area":"safety"},{"id":"2503.16693","title":"ATOM: A Framework of Detecting Query-Based Model Extraction Attacks for Graph Neural Networks","created":"2025-03-20","cited_by_count":8,"area":null},{"id":"2504.13416","title":"STAMP Your Content: Proving Dataset Membership via Watermarked Rephrasings","created":"2025-04-18","cited_by_count":8,"area":null},{"id":"2506.02362","title":"MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2507.05622","title":"DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective","created":"2025-07-08","cited_by_count":8,"area":null},{"id":"2410.13088","title":"Self-Comparison for Dataset-Level Membership Inference in Large (Vision-)Language Models","created":"2024-10-16","cited_by_count":7,"area":"mllm"},{"id":"2506.15271","title":"Unlocking Post-hoc Dataset Inference with Synthetic Data","created":"2025-06-18","cited_by_count":7,"area":"synth"},{"id":"2312.04542","title":"SoK: Unintended Interactions among Machine Learning Defenses and Risks","created":"2023-12-07","cited_by_count":6,"area":null},{"id":"2412.13475","title":"A Statistical and Multi-Perspective Revisiting of the Membership Inference Attack in Large Language Models","created":"2024-12-18","cited_by_count":6,"area":"safety"},{"id":"2602.03812","title":"Antidistillation Fingerprinting","created":"2026-02-03","cited_by_count":6,"area":null},{"id":"2209.03620","title":"Black-Box Audits for Group Distribution Shifts","created":"2022-09-08","cited_by_count":5,"area":null},{"id":"2502.08211","title":"Quality over Quantity: Boosting Data Efficiency Through Ensembled Multimodal Data Curation","created":"2025-02-12","cited_by_count":5,"area":null},{"id":"2507.08983","title":"Exploiting Leaderboards for Large-Scale Distribution of Malicious Models","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2109.09023","title":"Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Networks","created":"2021-09-18","cited_by_count":4,"area":null},{"id":"2210.11728","title":"Distilling the Undistillable: Learning from a Nasty Teacher","created":"2022-10-21","cited_by_count":4,"area":"distill"},{"id":"2308.12319","title":"RemovalNet: DNN Fingerprint Removal Attacks","created":"2023-08-23","cited_by_count":4,"area":null},{"id":"2310.01959","title":"Beyond Labeling Oracles: What does it mean to steal ML models?","created":"2023-10-03","cited_by_count":4,"area":null},{"id":"2405.15161","title":"Are You Copying My Prompt? Protecting the Copyright of Vision Prompt for VPaaS via Watermark","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2409.06280","title":"Anonymity Unveiled: A Practical Framework for Auditing Data Use in Deep Learning Models","created":"2024-09-10","cited_by_count":4,"area":null},{"id":"2503.22413","title":"Instance-Level Data-Use Auditing of Visual ML Models","created":"2025-03-28","cited_by_count":4,"area":"safety"},{"id":"2505.22356","title":"Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settings","created":"2025-05-28","cited_by_count":4,"area":null},{"id":"2510.09655","title":"Data Provenance Auditing of Fine-Tuned Large Language Models with a Text-Preserving Technique","created":"2025-10-07","cited_by_count":4,"area":null},{"id":"2306.09951","title":"You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2306.11338","title":"FDINet: Protecting against DNN Model Extraction via Feature Distortion Index","created":"2023-06-20","cited_by_count":3,"area":null},{"id":"2502.09974","title":"Has My System Prompt Been Used? Large Language Model Prompt Membership Inference","created":"2025-02-14","cited_by_count":3,"area":"safety"},{"id":"2506.06057","title":"Hey, That's My Data! Token-Only Dataset Inference in Large Language Models","created":"2025-06-06","cited_by_count":3,"area":null},{"id":"2508.14062","title":"Assessing and Mitigating Data Memorization Risks in Fine-Tuned Large Language Models","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2510.05699","title":"Membership Inference Attacks on Tokenizers of Large Language Models","created":"2025-10-07","cited_by_count":3,"area":"safety"},{"id":"2511.04711","title":"SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking","created":"2025-11-05","cited_by_count":3,"area":"mllm"},{"id":"2211.13416","title":"Data Origin Inference in Machine Learning","created":"2022-11-24","cited_by_count":2,"area":null},{"id":"2403.10663","title":"Not Just Change the Labels, Learn the Features: Watermarking Deep Neural Networks with Multi-View Data","created":"2024-03-15","cited_by_count":2,"area":null},{"id":"2405.00466","title":"Lazy Layers to Make Fine-Tuned Diffusion Models More Traceable","created":"2024-05-01","cited_by_count":2,"area":"diffusion"},{"id":"2411.09776","title":"Combining Machine Learning Defenses without Conflicts","created":"2024-11-14","cited_by_count":2,"area":null},{"id":"2502.15836","title":"Soft Token Attacks Cannot Reliably Audit Unlearning in Large Language Models","created":"2025-02-20","cited_by_count":2,"area":"safety"},{"id":"2503.00065","title":"ADAGE: Active Defenses Against GNN Extraction","created":"2025-02-27","cited_by_count":2,"area":null},{"id":"2507.00724","title":"Holmes: Towards Effective and Harmless Model Ownership Verification to Personalized Large Vision Models via Decoupling Common Features","created":"2025-06-24","cited_by_count":2,"area":null},{"id":"2507.12022","title":"Dataset Ownership Verification for Pre-trained Masked Models","created":"2025-07-16","cited_by_count":2,"area":null},{"id":"2508.01074","title":"Evading Data Provenance in Deep Neural Networks","created":"2025-08-01","cited_by_count":2,"area":null},{"id":"2510.16968","title":"Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures","created":"2025-10-19","cited_by_count":2,"area":"moe"},{"id":"2512.09654","title":"Membership and Dataset Inference Attacks on Large Audio Generative Models","created":"2025-12-10","cited_by_count":2,"area":"safety"},{"id":"2601.04301","title":"Quantifying the Effect of Test Set Contamination on Generative Evaluations","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2602.02819","title":"Causal Evaluation of Membership Inference Attacks","created":"2026-02-02","cited_by_count":2,"area":"safety"},{"id":"2608.04314","title":"Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle","created":"2026-08-05","cited_by_count":2,"area":null},{"id":"2306.05233","title":"Ownership Protection of Generative Adversarial Networks","created":"2023-06-08","cited_by_count":1,"area":null},{"id":"2308.02121","title":"Model Provenance via Model DNA","created":"2023-08-04","cited_by_count":1,"area":null},{"id":"2408.02140","title":"VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional Spaces","created":"2024-08-04","cited_by_count":1,"area":null},{"id":"2504.11509","title":"PATFinger: Prompt-Adapted Transferable Fingerprinting against Unauthorized Multimodal Dataset Usage","created":"2025-04-15","cited_by_count":1,"area":"mllm"},{"id":"2505.11110","title":"Deepfake Forensic Analysis: Source Dataset Attribution and Legal Implications of Synthetic Media Manipulation","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2505.12058","title":"Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2507.06056","title":"Data Compressibility Quantifies LLM Memorization","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.12386","title":"Amulet: a Python Library for Assessing Interactions Among ML Defenses and Risks","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2512.14439","title":"VICTOR: Dataset Copyright Auditing in Video Recognition Systems","created":"2025-12-16","cited_by_count":1,"area":null},{"id":"2602.09284","title":"X-Mark: Saliency-Guided Robust Dataset Ownership Verification for Medical Imaging","created":"2026-02-10","cited_by_count":1,"area":"safety"},{"id":"2605.29245","title":"Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content","created":"2026-05-28","cited_by_count":1,"area":"safety"},{"id":"2605.30348","title":"LLMSurgeon: Diagnosing Data Mixture of Large Language Models","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2305.09058","title":"Private Training Set Inspection in MLaaS","created":"2023-05-15","cited_by_count":0,"area":null},{"id":"2310.10656","title":"VeriDIP: Verifying Ownership of Deep Neural Networks through Privacy Leakage Fingerprints","created":"2023-09-07","cited_by_count":0,"area":null},{"id":"2405.04108","title":"A2-DIDM: Privacy-preserving Accumulator-enabled Auditing for Distributed Identity of DNN Model","created":"2024-05-07","cited_by_count":0,"area":null}],"next_cursor":"100"}