{"total":91,"rows":[{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2103.14991","title":"Graph Unlearning","created":"2021-03-27","cited_by_count":138,"area":"safety"},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"area":"safety"},{"id":"2208.14933","title":"Membership Inference Attacks by Exploiting Loss Trajectory","created":"2022-08-31","cited_by_count":101,"area":"safety"},{"id":"2302.03162","title":"Protecting Language Generation Models via Invisible Watermarking","created":"2023-02-06","cited_by_count":90,"area":"safety"},{"id":"2102.02551","title":"ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models","created":"2021-02-04","cited_by_count":85,"area":"safety"},{"id":"2112.02701","title":"Protecting Intellectual Property of Language Generation APIs with Lexical Watermark","created":"2021-12-05","cited_by_count":84,"area":"safety"},{"id":"2101.01341","title":"Practical Blind Membership Inference Attack via Differential Comparisons","created":"2021-01-05","cited_by_count":78,"area":"safety"},{"id":"2209.08773","title":"CATER: Intellectual Property Protection on Text Generation APIs via Conditional Watermarks","created":"2022-09-19","cited_by_count":76,"area":"safety"},{"id":"2108.11023","title":"EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning","created":"2021-08-25","cited_by_count":73,"area":"safety"},{"id":"2110.08324","title":"Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture","created":"2021-10-15","cited_by_count":67,"area":"safety"},{"id":"2109.08045","title":"Membership Inference Attacks Against Recommender Systems","created":"2021-09-16","cited_by_count":57,"area":"safety"},{"id":"2404.03233","title":"Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning","created":"2024-04-04","cited_by_count":48,"area":"safety"},{"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":"2205.12709","title":"VeriFi: Towards Verifiable Federated Unlearning","created":"2022-05-25","cited_by_count":46,"area":"safety"},{"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":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"area":"safety"},{"id":"2109.13236","title":"FedIPR: Ownership Verification for Federated Deep Neural Network Models","created":"2021-09-27","cited_by_count":36,"area":"safety"},{"id":"2105.03592","title":"De-Pois: An Attack-Agnostic Defense against Data Poisoning Attacks","created":"2021-05-08","cited_by_count":33,"area":"safety"},{"id":"2111.07608","title":"Property Inference Attacks Against GANs","created":"2021-11-15","cited_by_count":33,"area":"safety"},{"id":"2303.03446","title":"Students Parrot Their Teachers: Membership Inference on Model Distillation","created":"2023-03-06","cited_by_count":33,"area":"safety"},{"id":"2305.17444","title":"Query-Efficient Black-Box Red Teaming via Bayesian Optimization","created":"2023-05-27","cited_by_count":32,"area":"safety"},{"id":"2411.11315","title":"A Review on Machine Unlearning","created":"2024-11-18","cited_by_count":32,"area":"safety"},{"id":"2103.07101","title":"On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models","created":"2021-03-12","cited_by_count":31,"area":"safety"},{"id":"2412.06157","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","created":"2024-12-09","cited_by_count":31,"area":"safety"},{"id":"2210.03312","title":"Distillation-Resistant Watermarking for Model Protection in NLP","created":"2022-10-07","cited_by_count":30,"area":"safety"},{"id":"2307.01610","title":"Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction","created":"2023-07-04","cited_by_count":29,"area":"safety"},{"id":"2303.09732","title":"Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation","created":"2023-03-17","cited_by_count":20,"area":"safety"},{"id":"2407.02551","title":"Breach By A Thousand Leaks: Unsafe Information Leakage in `Safe' AI Responses","created":"2024-07-02","cited_by_count":18,"area":"safety"},{"id":"2102.07762","title":"Membership Inference Attacks are Easier on Difficult Problems","created":"2021-02-15","cited_by_count":17,"area":"safety"},{"id":"2401.15239","title":"MEA-Defender: A Robust Watermark against Model Extraction Attack","created":"2024-01-26","cited_by_count":17,"area":"safety"},{"id":"2501.09798","title":"Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface","created":"2025-01-16","cited_by_count":17,"area":"safety"},{"id":"2111.05113","title":"Membership Inference Attacks Against Self-supervised Speech Models","created":"2021-11-09","cited_by_count":16,"area":"safety"},{"id":"2202.10276","title":"Poisoning Attacks and Defenses on Artificial Intelligence: A Survey","created":"2022-02-21","cited_by_count":16,"area":"safety"},{"id":"2210.11334","title":"Proof of Unlearning: Definitions and Instantiation","created":"2022-10-20","cited_by_count":15,"area":"safety"},{"id":"2406.06186","title":"A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks","created":"2024-06-10","cited_by_count":15,"area":"safety"},{"id":"2310.11397","title":"Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning","created":"2023-10-17","cited_by_count":14,"area":"safety"},{"id":"2203.02777","title":"Cosine Model Watermarking Against Ensemble Distillation","created":"2022-03-05","cited_by_count":13,"area":"safety"},{"id":"2304.11285","title":"Identifying Appropriate Intellectual Property Protection Mechanisms for Machine Learning Models: A Systematization of Watermarking, Fingerprinting, Model Access, and Attacks","created":"2023-04-22","cited_by_count":12,"area":"safety"},{"id":"2104.08273","title":"Membership Inference Attacks on Knowledge Graphs","created":"2021-04-16","cited_by_count":11,"area":"safety"},{"id":"2105.05381","title":"Accuracy-Privacy Trade-off in Deep Ensemble: A Membership Inference Perspective","created":"2021-05-12","cited_by_count":10,"area":"safety"},{"id":"2102.09751","title":"PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting","created":"2021-02-19","cited_by_count":9,"area":"safety"},{"id":"2505.23814","title":"Watermarking Without Standards Is Not AI Governance","created":"2025-05-27","cited_by_count":9,"area":"safety"},{"id":"2403.18774","title":"RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees","created":"2024-01-23","cited_by_count":8,"area":"safety"},{"id":"2502.19567","title":"Atlas: A Framework for ML Lifecycle Provenance & Transparency","created":"2025-02-26","cited_by_count":8,"area":"safety"},{"id":"2509.25448","title":"Fingerprinting LLMs via Prompt Injection","created":"2025-09-29","cited_by_count":8,"area":"safety"},{"id":"2405.02365","title":"ModelShield: Adaptive and Robust Watermark against Model Extraction Attack","created":"2024-05-03","cited_by_count":7,"area":"safety"},{"id":"2106.08104","title":"Detect and remove watermark in deep neural networks via generative adversarial networks","created":"2021-06-15","cited_by_count":6,"area":"safety"},{"id":"2111.01363","title":"Knowledge Cross-Distillation for Membership Privacy","created":"2021-11-02","cited_by_count":6,"area":"safety"},{"id":"2311.11796","title":"Beyond Boundaries: A Comprehensive Survey of Transferable Attacks on AI Systems","created":"2023-11-20","cited_by_count":6,"area":"safety"},{"id":"2407.01306","title":"Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability","created":"2024-07-01","cited_by_count":6,"area":"safety"},{"id":"2407.15526","title":"Synthetic Image Learning: Preserving Performance and Preventing Membership Inference Attacks","created":"2024-07-22","cited_by_count":5,"area":"safety"},{"id":"2409.03741","title":"Understanding Data Importance in Machine Learning Attacks: Does Valuable Data Pose Greater Harm?","created":"2024-09-05","cited_by_count":5,"area":"safety"},{"id":"2207.13321","title":"DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking","created":"2022-07-27","cited_by_count":4,"area":"safety"},{"id":"2310.12665","title":"SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models","created":"2023-10-19","cited_by_count":4,"area":"safety"},{"id":"2402.19054","title":"RobWE: Robust Watermark Embedding for Personalized Federated Learning Model Ownership Protection","created":"2024-02-29","cited_by_count":4,"area":"safety"},{"id":"2405.15316","title":"Decaf: Data Distribution Decompose Attack against Federated Learning","created":"2024-05-24","cited_by_count":4,"area":"safety"},{"id":"2607.03688","title":"PathMark: Protecting Intellectual Property of Mixture-of-Expert LLMs via Path Watermarks","created":"2026-07-04","cited_by_count":4,"area":"safety"},{"id":"2206.05565","title":"NeuGuard: Lightweight Neuron-Guided Defense against Membership Inference Attacks","created":"2022-06-11","cited_by_count":3,"area":"safety"},{"id":"2409.06130","title":"Revisiting Black-Box Model Ownership Verification through Information Theory","created":"2024-09-10","cited_by_count":3,"area":"safety"},{"id":"2502.16737","title":"Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning","created":"2025-02-23","cited_by_count":3,"area":"safety"},{"id":"2603.07567","title":"Revisiting the LiRA Membership Inference Attack Under Realistic Assumptions","created":"2026-03-08","cited_by_count":3,"area":"safety"},{"id":"2606.10813","title":"RedAct: Redacting Agent Capability Traces for Procedural Skill Protection","created":"2026-06-09","cited_by_count":3,"area":"safety"},{"id":"2210.11592","title":"New data poison attacks on machine learning classifiers for mobile exfiltration","created":"2022-10-20","cited_by_count":2,"area":"safety"},{"id":"2210.16258","title":"On the Vulnerability of Data Points under Multiple Membership Inference Attacks and Target Models","created":"2022-10-28","cited_by_count":2,"area":"safety"},{"id":"2402.06864","title":"Discriminative Adversarial Unlearning","created":"2024-02-10","cited_by_count":2,"area":"safety"},{"id":"2410.14102","title":"Beyond Dataset Watermarking: Model-Level Copyright Protection for Code Summarization Models","created":"2024-10-18","cited_by_count":2,"area":"safety"},{"id":"2503.23748","title":"THEMIS: Towards Practical Intellectual Property Protection for Post-Deployment On-Device Deep Learning Models","created":"2025-03-31","cited_by_count":2,"area":"safety"},{"id":"2507.13591","title":"FuSeFL: Fully Secure and Scalable Federated Learning","created":"2025-07-18","cited_by_count":2,"area":"safety"},{"id":"2108.02360","title":"Exploring Structure Consistency for Deep Model Watermarking","created":"2021-08-05","cited_by_count":1,"area":"safety"},{"id":"2401.13719","title":"Inference Attacks Against Face Recognition Model without Classification Layers","created":"2024-01-24","cited_by_count":1,"area":"safety"},{"id":"2411.16769","title":"Red-Teaming Text-to-Image Models via In-Context Experience Replay and Semantic-Preserving Prompt Rewriting","created":"2024-11-25","cited_by_count":1,"area":"safety"},{"id":"2601.01296","title":"Aggressive Compression Enables LLM Weight Theft","created":"2026-01-03","cited_by_count":1,"area":"safety"},{"id":"2602.23587","title":"PDF: PUF-based DNN Fingerprinting for Knowledge Distillation Traceability","created":"2026-02-27","cited_by_count":1,"area":"safety"},{"id":"2603.07835","title":"DistillGuard: Evaluating Defenses Against LLM Knowledge Distillation","created":"2026-03-08","cited_by_count":1,"area":"safety"},{"id":"2603.12023","title":"Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems","created":"2026-03-12","cited_by_count":1,"area":"safety"},{"id":"2603.24857","title":"AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective","created":"2026-03-25","cited_by_count":1,"area":"safety"},{"id":"2209.11020","title":"Privacy Attacks Against Biometric Models with Fewer Samples: Incorporating the Output of Multiple Models","created":"2022-09-22","cited_by_count":0,"area":"safety"},{"id":"2211.13644","title":"Seeds Don't Lie: An Adaptive Watermarking Framework for Computer Vision Models","created":"2022-11-24","cited_by_count":0,"area":"safety"},{"id":"2411.13047","title":"Bounding-box Watermarking: Defense against Model Extraction Attacks on Object Detectors","created":"2024-11-20","cited_by_count":0,"area":"safety"},{"id":"2501.09328","title":"Neural Honeytrace: Plug&Play Watermarking Framework against Model Extraction Attacks","created":"2025-01-16","cited_by_count":0,"area":"safety"},{"id":"2505.24536","title":"CHIP: Chameleon Hash-based Irreversible Passport for Robust Deep Model Ownership Verification and Active Usage Control","created":"2025-05-30","cited_by_count":0,"area":"safety"},{"id":"2511.01377","title":"Protecting the Neural Networks against FGSM Attack Using Machine Unlearning","created":"2025-11-03","cited_by_count":0,"area":"safety"},{"id":"2511.04215","title":"Black-Box Guardrail Reverse-engineering Attack","created":"2025-11-06","cited_by_count":0,"area":"safety"},{"id":"2511.07947","title":"Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks","created":"2025-11-11","cited_by_count":0,"area":"safety"},{"id":"2602.03567","title":"EVE: Efficient Verification of Data Erasure through Customized Perturbation in Approximate Unlearning","created":"2026-02-03","cited_by_count":0,"area":"safety"},{"id":"2602.18934","title":"LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings","created":"2026-02-21","cited_by_count":0,"area":"safety"},{"id":"2604.02780","title":"A Unified Perspective on Adversarial Membership Manipulation in Vision Models","created":"2026-04-03","cited_by_count":0,"area":"safety"},{"id":"2605.20286","title":"Adaptive Probe-based Steering for Robust LLM Jailbreaking","created":"2026-05-19","cited_by_count":0,"area":"safety"},{"id":"2606.11698","title":"T2S: A Rehearsal-Based Approach for Extraction-Resistant Model Watermarking","created":"2026-06-10","cited_by_count":0,"area":"safety"},{"id":"2607.10794","title":"Can Watermarking Techniques Help Prevent LLM Model Stealing?","created":"2026-07-12","cited_by_count":0,"area":"safety"}],"next_cursor":null}