{"total":44,"rows":[{"id":"2310.02446","title":"Low-Resource Languages Jailbreak GPT-4","created":"2023-10-03","cited_by_count":309,"area":"safety"},{"id":"2201.05629","title":"Zero-Shot Machine Unlearning","created":"2022-01-14","cited_by_count":133,"area":"safety"},{"id":"2104.10706","title":"Dataset Inference: Ownership Resolution in Machine Learning","created":"2021-04-21","cited_by_count":116,"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":"2104.09667","title":"Manipulating SGD with Data Ordering Attacks","created":"2021-04-19","cited_by_count":74,"area":"safety"},{"id":"2302.04237","title":"Black Box Adversarial Prompting for Foundation Models","created":"2023-02-08","cited_by_count":62,"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":"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":"2111.07608","title":"Property Inference Attacks Against GANs","created":"2021-11-15","cited_by_count":33,"area":"safety"},{"id":"2404.07234","title":"Goal-guided Generative Prompt Injection Attack on Large Language Models","created":"2024-04-06","cited_by_count":24,"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":"2208.10445","title":"Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models","created":"2022-08-22","cited_by_count":16,"area":"safety"},{"id":"2203.02777","title":"Cosine Model Watermarking Against Ensemble Distillation","created":"2022-03-05","cited_by_count":13,"area":"safety"},{"id":"2106.00660","title":"Markpainting: Adversarial Machine Learning meets Inpainting","created":"2021-06-01","cited_by_count":9,"area":"safety"},{"id":"2404.13518","title":"Reliable Model Watermarking: Defending Against Theft without Compromising on Evasion","created":"2024-04-21","cited_by_count":9,"area":"safety"},{"id":"2407.01251","title":"QUEEN: Query Unlearning against Model Extraction","created":"2024-07-01","cited_by_count":9,"area":"safety"},{"id":"2308.07847","title":"Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models","created":"2023-08-15","cited_by_count":7,"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":"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":"2502.16423","title":"Unified Prompt Attack Against Text-to-Image Generation Models","created":"2025-02-23","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":"2302.06801","title":"Backdoor Learning for NLP: Recent Advances, Challenges, and Future Research Directions","created":"2023-02-14","cited_by_count":4,"area":"safety"},{"id":"2312.14260","title":"Elevating Defenses: Bridging Adversarial Training and Watermarking for Model Resilience","created":"2023-12-21","cited_by_count":3,"area":"safety"},{"id":"2501.16534","title":"Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs","created":"2025-01-27","cited_by_count":3,"area":"safety"},{"id":"2503.00062","title":"CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning","created":"2025-02-27","cited_by_count":3,"area":"safety"},{"id":"2211.13535","title":"DeepTaster: Adversarial Perturbation-Based Fingerprinting to Identify Proprietary Dataset Use in Deep Neural Networks","created":"2022-11-24","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":"2506.05376","title":"A Red Teaming Roadmap Towards System-Level Safety","created":"2025-05-30","cited_by_count":2,"area":"safety"},{"id":"2205.08821","title":"Lessons Learned: Defending Against Property Inference Attacks","created":"2022-05-18","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":"2510.01494","title":"Understanding Adversarial Transfer: Why Representation-Space Attacks Fail Where Data-Space Attacks Succeed","created":"2025-10-01","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":"2105.13530","title":"A BIC-based Mixture Model Defense against Data Poisoning Attacks on Classifiers","created":"2021-05-28","cited_by_count":0,"area":"safety"},{"id":"2202.10309","title":"HoneyModels: Machine Learning Honeypots","created":"2022-02-21","cited_by_count":0,"area":"safety"},{"id":"2309.13579","title":"Seeing Is Not Always Believing: Invisible Collision Attack and Defence on Pre-Trained Models","created":"2023-09-24","cited_by_count":0,"area":"safety"},{"id":"2506.20926","title":"Towards Generalized and Stealthy Watermarking for Generative Code Models","created":"2025-06-26","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":"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":"2606.20746","title":"Amplify, Don't Create: Temporal Accumulation for Slow-Burn Prompt Injection","created":"2026-06-17","cited_by_count":0,"area":"safety"},{"id":"2607.28187","title":"Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation","created":"2026-07-30","cited_by_count":0,"area":"safety"},{"id":"2609.24801","title":"Decoding Guardrails: XAI-Guided Perturbation Analysis of Prompt Injection Detection","created":"2026-09-21","cited_by_count":0,"area":"safety"}],"next_cursor":null}