{"total":175,"rows":[{"id":"2308.03825","title":"\"Do Anything Now\": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models","created":"2023-08-07","cited_by_count":489,"area":"safety"},{"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":"2302.00539","title":"Analyzing Leakage of Personally Identifiable Information in Language Models","created":"2023-02-01","cited_by_count":285,"area":"safety"},{"id":"2305.18462","title":"Membership Inference Attacks against Language Models via Neighbourhood Comparison","created":"2023-05-29","cited_by_count":258,"area":"safety"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2205.10770","title":"Memorization Without Overfitting: Analyzing the Training Dynamics of Large Language Models","created":"2022-05-22","cited_by_count":220,"area":null},{"id":"2503.21460","title":"Large Language Model Agent: A Survey on Methodology, Applications and Challenges","created":"2025-03-27","cited_by_count":205,"area":"agents"},{"id":"2402.07841","title":"Do Membership Inference Attacks Work on Large Language Models?","created":"2024-02-12","cited_by_count":195,"area":"safety"},{"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":"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":"2311.06062","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","created":"2023-11-10","cited_by_count":98,"area":"safety"},{"id":"2402.05668","title":"JailbreakRadar: Comprehensive Assessment of Jailbreak Attacks Against LLMs","created":"2024-02-08","cited_by_count":95,"area":"safety"},{"id":"2401.06059","title":"Investigating Data Contamination for Pre-training Language Models","created":"2024-01-11","cited_by_count":91,"area":null},{"id":"2403.17336","title":"Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models","created":"2024-03-26","cited_by_count":86,"area":"safety"},{"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":"2308.16149","title":"Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models","created":"2023-08-30","cited_by_count":69,"area":null},{"id":"2406.15968","title":"ReCaLL: Membership Inference via Relative Conditional Log-Likelihoods","created":"2024-06-23","cited_by_count":64,"area":"safety"},{"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":"2310.10383","title":"Privacy in Large Language Models: Attacks, Defenses and Future Directions","created":"2023-10-16","cited_by_count":51,"area":null},{"id":"2402.10052","title":"UNDIAL: Self-Distillation with Adjusted Logits for Robust Unlearning in Large Language Models","created":"2024-02-15","cited_by_count":50,"area":"safety"},{"id":"2302.07225","title":"Bounding Training Data Reconstruction in DP-SGD","created":"2023-02-14","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":"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":"2401.04343","title":"Private Fine-tuning of Large Language Models with Zeroth-order Optimization","created":"2024-01-09","cited_by_count":41,"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":"2402.09363","title":"Copyright Traps for Large Language Models","created":"2024-02-14","cited_by_count":37,"area":null},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37,"area":"safety"},{"id":"2307.04401","title":"Ethicist: Targeted Training Data Extraction Through Loss Smoothed Soft Prompting and Calibrated Confidence Estimation","created":"2023-07-10","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":"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":"2305.09859","title":"Smaller Language Models are Better Black-box Machine-Generated Text Detectors","created":"2023-05-17","cited_by_count":35,"area":null},{"id":"2405.16281","title":"ConStat: Performance-Based Contamination Detection in Large Language Models","created":"2024-05-25","cited_by_count":33,"area":null},{"id":"2411.03923","title":"Evaluation data contamination in LLMs: how do we measure it and (when) does it matter?","created":"2024-11-06","cited_by_count":32,"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":"2312.11658","title":"Traces of Memorisation in Large Language Models for Code","created":"2023-12-18","cited_by_count":29,"area":"safety"},{"id":"2410.02650","title":"Undesirable Memorization in Large Language Models: A Survey","created":"2024-10-03","cited_by_count":29,"area":null},{"id":"2305.13257","title":"Watermarking Text Data on Large Language Models for Dataset Copyright","created":"2023-05-22","cited_by_count":27,"area":"safety"},{"id":"2409.14457","title":"Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends","created":"2024-09-22","cited_by_count":26,"area":null},{"id":"2410.18966","title":"Does Data Contamination Detection Work (Well) for LLMs? A Survey and Evaluation on Detection Assumptions","created":"2024-10-24","cited_by_count":26,"area":null},{"id":"2401.00676","title":"Digger: Detecting Copyright Content Mis-usage in Large Language Model Training","created":"2024-01-01","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":"2405.11930","title":"Data Contamination Calibration for Black-box LLMs","created":"2024-05-20","cited_by_count":24,"area":null},{"id":"2403.09562","title":"PreCurious: How Innocent Pre-Trained Language Models Turn into Privacy Traps","created":"2024-03-14","cited_by_count":23,"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":"2409.11423","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","created":"2024-09-12","cited_by_count":22,"area":"synth"},{"id":"2409.13745","title":"Context-Aware Membership Inference Attacks against Pre-trained Large Language Models","created":"2024-09-11","cited_by_count":22,"area":"safety"},{"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":"2509.14284","title":"The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration","created":"2025-09-16","cited_by_count":20,"area":"agents"},{"id":"2205.14055","title":"A Blessing of Dimensionality in Membership Inference through Regularization","created":"2022-05-27","cited_by_count":18,"area":"safety"},{"id":"2403.10557","title":"Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models","created":"2024-03-13","cited_by_count":18,"area":"safety"},{"id":"2407.17417","title":"Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?","created":"2024-07-24","cited_by_count":18,"area":"safety"},{"id":"2503.19338","title":"Membership Inference Attacks on Large-Scale Models: A Survey","created":"2025-03-25","cited_by_count":18,"area":"mllm"},{"id":"2209.08615","title":"Membership Inference Attacks and Generalization: A Causal Perspective","created":"2022-09-18","cited_by_count":17,"area":"safety"},{"id":"2305.15008","title":"Are Chatbots Ready for Privacy-Sensitive Applications? An Investigation into Input Regurgitation and Prompt-Induced Sanitization","created":"2023-05-24","cited_by_count":17,"area":null},{"id":"2404.16841","title":"Machine Unlearning in Large Language Models","created":"2024-02-03","cited_by_count":17,"area":"safety"},{"id":"2406.10218","title":"Semantic Membership Inference Attack against Large Language Models","created":"2024-06-14","cited_by_count":17,"area":"safety"},{"id":"2307.10476","title":"What can we learn from Data Leakage and Unlearning for Law?","created":"2023-07-19","cited_by_count":15,"area":"safety"},{"id":"2506.02959","title":"HACo-Det: A Study Towards Fine-Grained Machine-Generated Text Detection under Human-AI Coauthoring","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2507.06969","title":"Unifying Re-Identification, Attribute Inference, and Data Reconstruction Risks in Differential Privacy","created":"2025-07-09","cited_by_count":15,"area":null},{"id":"2309.07983","title":"SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems","created":"2023-09-14","cited_by_count":14,"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":"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":"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":"2410.07582","title":"Detecting Training Data of Large Language Models via Expectation Maximization","created":"2024-10-10","cited_by_count":13,"area":"safety"},{"id":"2506.11680","title":"Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information","created":"2025-06-13","cited_by_count":13,"area":null},{"id":"2212.10520","title":"Privacy-Preserving Domain Adaptation of Semantic Parsers","created":"2022-12-20","cited_by_count":12,"area":null},{"id":"2309.16398","title":"Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey","created":"2023-09-28","cited_by_count":12,"area":null},{"id":"2311.11415","title":"A Security Risk Taxonomy for Prompt-Based Interaction With Large Language Models","created":"2023-11-19","cited_by_count":12,"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":"2502.12658","title":"R.R.: Unveiling LLM Training Privacy through Recollection and Ranking","created":"2025-02-18","cited_by_count":10,"area":"safety"},{"id":"2503.07384","title":"Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs","created":"2025-03-10","cited_by_count":10,"area":"safety"},{"id":"2310.16152","title":"Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering","created":"2023-10-24","cited_by_count":9,"area":null},{"id":"2507.18302","title":"LoRA-Leak: Membership Inference Attacks Against LoRA Fine-tuned Language Models","created":"2025-07-24","cited_by_count":9,"area":"safety"},{"id":"2302.07735","title":"Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge","created":"2023-02-13","cited_by_count":8,"area":"safety"},{"id":"2310.13291","title":"Assessing Privacy Risks in Language Models: A Case Study on Summarization Tasks","created":"2023-10-20","cited_by_count":8,"area":null},{"id":"2312.07200","title":"Code Membership Inference for Detecting Unauthorized Data Use in Code Pre-trained Language Models","created":"2023-12-12","cited_by_count":8,"area":"safety"},{"id":"2404.05783","title":"A Survey on Responsible Generative AI: What to Generate and What Not","created":"2024-04-08","cited_by_count":8,"area":null},{"id":"2406.11380","title":"Evaluating LLMs for Quotation Attribution in Literary Texts: A Case Study of LLaMa3","created":"2024-06-17","cited_by_count":8,"area":null},{"id":"2411.10670","title":"IntentGPT: Few-shot Intent Discovery with Large Language Models","created":"2024-11-16","cited_by_count":8,"area":null},{"id":"2501.03941","title":"Synthetic Data Privacy Metrics","created":"2025-01-07","cited_by_count":8,"area":null},{"id":"2503.06040","title":"Mitigating Memorization in LLMs using Activation Steering","created":"2025-03-08","cited_by_count":8,"area":"mechinterp"},{"id":"2503.12072","title":"Information-Guided Identification of Training Data Imprint in (Proprietary) Large Language Models","created":"2025-03-15","cited_by_count":8,"area":null},{"id":"2310.07219","title":"Improved Membership Inference Attacks Against Language Classification Models","created":"2023-10-11","cited_by_count":7,"area":"safety"},{"id":"2407.01919","title":"A Method to Facilitate Membership Inference Attacks in Deep Learning Models","created":"2024-07-02","cited_by_count":7,"area":"safety"},{"id":"2502.05087","title":"Mitigating Unintended Memorization with LoRA in Federated Learning for LLMs","created":"2025-02-07","cited_by_count":7,"area":null},{"id":"2505.22860","title":"Permissioned LLMs: Enforcing Access Control in Large Language Models","created":"2025-05-28","cited_by_count":7,"area":null},{"id":"2506.10024","title":"Private Memorization Editing: Turning Memorization into a Defense to Strengthen Data Privacy in Large Language Models","created":"2025-06-09","cited_by_count":7,"area":null},{"id":"2507.21198","title":"Uncovering Gradient Inversion Risks in Practical Language Model Training","created":"2025-07-28","cited_by_count":7,"area":null},{"id":"2508.09603","title":"The Surprising Effectiveness of Membership Inference with Simple N-Gram Coverage","created":"2025-08-13","cited_by_count":7,"area":"safety"},{"id":"2601.02751","title":"Window-based Membership Inference Attacks Against Fine-tuned Large Language Models","created":"2026-01-06","cited_by_count":7,"area":"safety"},{"id":"2305.07882","title":"Dual Use Concerns of Generative AI and Large Language Models","created":"2023-05-13","cited_by_count":6,"area":null},{"id":"2402.05453","title":"Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss","created":"2024-02-08","cited_by_count":6,"area":"safety"},{"id":"2406.18326","title":"PaCoST: Paired Confidence Significance Testing for Benchmark Contamination Detection in Large Language Models","created":"2024-06-26","cited_by_count":6,"area":null},{"id":"2409.03274","title":"Recent Advances in Attack and Defense Approaches of Large Language Models","created":"2024-09-05","cited_by_count":6,"area":null},{"id":"2502.17259","title":"Detecting Benchmark Contamination Through Watermarking","created":"2025-02-24","cited_by_count":6,"area":null},{"id":"2506.14913","title":"Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning","created":"2025-06-17","cited_by_count":6,"area":"safety"}],"next_cursor":"100"}