{"total":203,"rows":[{"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":"2304.05197","title":"Multi-step Jailbreaking Privacy Attacks on ChatGPT","created":"2023-04-11","cited_by_count":333,"area":"safety"},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321,"area":"safety"},{"id":"2202.06539","title":"Deduplicating Training Data Mitigates Privacy Risks in Language Models","created":"2022-02-14","cited_by_count":314,"area":null},{"id":"2407.06460","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","created":"2024-07-08","cited_by_count":261,"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":"2111.09679","title":"Enhanced Membership Inference Attacks against Machine Learning Models","created":"2021-11-18","cited_by_count":248,"area":"safety"},{"id":"2309.15025","title":"Large Language Model Alignment: A Survey","created":"2023-09-26","cited_by_count":243,"area":"alignment"},{"id":"2202.05520","title":"What Does it Mean for a Language Model to Preserve Privacy?","created":"2022-02-11","cited_by_count":195,"area":null},{"id":"2310.06816","title":"Text Embeddings Reveal (Almost) As Much As Text","created":"2023-10-10","cited_by_count":192,"area":null},{"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":"2203.03929","title":"Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks","created":"2022-03-08","cited_by_count":175,"area":"safety"},{"id":"2406.02630","title":"AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways","created":"2024-06-04","cited_by_count":127,"area":null},{"id":"2207.00220","title":"Pile of Law: Learning Responsible Data Filtering from the Law and a 256GB Open-Source Legal Dataset","created":"2022-07-01","cited_by_count":113,"area":null},{"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":"2308.12833","title":"Use of LLMs for Illicit Purposes: Threats, Prevention Measures, and Vulnerabilities","created":"2023-08-24","cited_by_count":82,"area":null},{"id":"2305.03010","title":"Sentence Embedding Leaks More Information than You Expect: Generative Embedding Inversion Attack to Recover the Whole Sentence","created":"2023-05-04","cited_by_count":81,"area":null},{"id":"2106.01221","title":"Differential Privacy for Text Analytics via Natural Text Sanitization","created":"2021-06-02","cited_by_count":77,"area":null},{"id":"2212.10025","title":"When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods","created":"2022-12-20","cited_by_count":75,"area":null},{"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":"2205.08514","title":"Recovering Private Text in Federated Learning of Language Models","created":"2022-05-17","cited_by_count":70,"area":null},{"id":"2210.13918","title":"Differentially Private Language Models for Secure Data Sharing","created":"2022-10-25","cited_by_count":68,"area":null},{"id":"2311.13647","title":"Language Model Inversion","created":"2023-11-22","cited_by_count":68,"area":null},{"id":"2309.06746","title":"DP-Forward: Fine-tuning and Inference on Language Models with Differential Privacy in Forward Pass","created":"2023-09-13","cited_by_count":67,"area":"safety"},{"id":"2205.02130","title":"The Limits of Word Level Differential Privacy","created":"2022-05-02","cited_by_count":63,"area":null},{"id":"2406.17975","title":"SoK: Membership Inference Attacks on LLMs are Rushing Nowhere (and How to Fix It)","created":"2024-06-25","cited_by_count":59,"area":"safety"},{"id":"2212.14315","title":"\"Real Attackers Don't Compute Gradients\": Bridging the Gap Between Adversarial ML Research and Practice","created":"2022-12-29","cited_by_count":56,"area":null},{"id":"2104.07504","title":"Natural Language Understanding with Privacy-Preserving BERT","created":"2021-04-15","cited_by_count":55,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2207.01193","title":"A Customized Text Sanitization Mechanism with Differential Privacy","created":"2022-07-04","cited_by_count":52,"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":"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":"2305.16157","title":"Training Data Extraction From Pre-trained Language Models: A Survey","created":"2023-05-25","cited_by_count":45,"area":null},{"id":"2305.06212","title":"Privacy-Preserving Parameter-Efficient Fine-Tuning for Large Language Model Services","created":"2023-05-10","cited_by_count":43,"area":null},{"id":"2405.15012","title":"Extracting Prompts by Inverting LLM Outputs","created":"2024-05-23","cited_by_count":41,"area":null},{"id":"2311.04044","title":"PrivLM-Bench: A Multi-level Privacy Evaluation Benchmark for Language Models","created":"2023-11-07","cited_by_count":37,"area":null},{"id":"2102.04140","title":"Quantifying and Mitigating Privacy Risks of Contrastive Learning","created":"2021-02-08","cited_by_count":36,"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":"2106.11384","title":"Membership Inference on Word Embedding and Beyond","created":"2021-06-21","cited_by_count":35,"area":"safety"},{"id":"2209.06997","title":"M^4I: Multi-modal Models Membership Inference","created":"2022-09-15","cited_by_count":34,"area":"safety"},{"id":"2209.03463","title":"Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots","created":"2022-09-07","cited_by_count":33,"area":null},{"id":"2407.18369","title":"AI Safety in Generative AI Large Language Models: A Survey","created":"2024-07-06","cited_by_count":33,"area":null},{"id":"2411.02902","title":"Membership Inference Attacks against Large Vision-Language Models","created":"2024-11-05","cited_by_count":33,"area":"mllm"},{"id":"2307.08925","title":"Integration of Large Language Models and Federated Learning","created":"2023-07-18","cited_by_count":31,"area":null},{"id":"2206.05483","title":"Bilateral Dependency Optimization: Defending Against Model-inversion Attacks","created":"2022-06-11","cited_by_count":30,"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":"2402.04013","title":"Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses","created":"2024-02-06","cited_by_count":30,"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":"2401.12192","title":"Text Embedding Inversion Security for Multilingual Language Models","created":"2024-01-22","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":"2406.10280","title":"Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries","created":"2024-06-12","cited_by_count":25,"area":null},{"id":"2311.17431","title":"Grounding Foundation Models through Federated Transfer Learning: A General Framework","created":"2023-11-29","cited_by_count":24,"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":"2108.12318","title":"CAPE: Context-Aware Private Embeddings for Private Language Learning","created":"2021-08-27","cited_by_count":22,"area":null},{"id":"2203.13920","title":"Canary Extraction in Natural Language Understanding Models","created":"2022-03-25","cited_by_count":21,"area":null},{"id":"2209.01100","title":"Group Property Inference Attacks Against Graph Neural Networks","created":"2022-09-02","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":"2506.03179","title":"Vid-SME: Membership Inference Attacks against Large Video Understanding Models","created":"2025-05-29","cited_by_count":19,"area":"mllm"},{"id":"2108.06910","title":"A Novel Attribute Reconstruction Attack in Federated Learning","created":"2021-08-16","cited_by_count":18,"area":null},{"id":"2408.10053","title":"Privacy Checklist: Privacy Violation Detection Grounding on Contextual Integrity Theory","created":"2024-08-19","cited_by_count":18,"area":null},{"id":"2504.16420","title":"A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms","created":"2025-04-23","cited_by_count":17,"area":"agents"},{"id":"2507.16372","title":"Depth Gives a False Sense of Privacy: LLM Internal States Inversion","created":"2025-07-22","cited_by_count":17,"area":null},{"id":"2111.05113","title":"Membership Inference Attacks Against Self-supervised Speech Models","created":"2021-11-09","cited_by_count":16,"area":"safety"},{"id":"2205.04605","title":"Sentence-level Privacy for Document Embeddings","created":"2022-05-10","cited_by_count":16,"area":null},{"id":"2205.10095","title":"How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing","created":"2022-05-20","cited_by_count":16,"area":null},{"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":"2302.09270","title":"Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements","created":"2023-02-18","cited_by_count":14,"area":null},{"id":"2306.01471","title":"Guiding Text-to-Text Privatization by Syntax","created":"2023-06-02","cited_by_count":14,"area":null},{"id":"2405.20771","title":"Towards Black-Box Membership Inference Attack for Diffusion Models","created":"2024-05-25","cited_by_count":14,"area":"diffusion"},{"id":"2404.03324","title":"A Comparative Analysis of Word-Level Metric Differential Privacy: Benchmarking The Privacy-Utility Trade-off","created":"2024-04-04","cited_by_count":13,"area":null},{"id":"2405.20681","title":"No Free Lunch Theorem for Privacy-Preserving LLM Inference","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2501.14224","title":"Top Ten Challenges Towards Agentic Neural Graph Databases","created":"2025-01-24","cited_by_count":13,"area":"agents"},{"id":"2204.09391","title":"You Are What You Write: Preserving Privacy in the Era of Large Language Models","created":"2022-04-20","cited_by_count":12,"area":null},{"id":"2208.08140","title":"Differential Privacy in Natural Language Processing: The Story So Far","created":"2022-08-17","cited_by_count":12,"area":null},{"id":"2403.14111","title":"HETAL: Efficient Privacy-preserving Transfer Learning with Homomorphic Encryption","created":"2024-03-21","cited_by_count":12,"area":null},{"id":"2405.08120","title":"From Questions to Insightful Answers: Building an Informed Chatbot for University Resources","created":"2024-05-13","cited_by_count":12,"area":"rag"},{"id":"2109.10104","title":"InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline","created":"2021-09-21","cited_by_count":11,"area":null},{"id":"2312.15603","title":"A Split-and-Privatize Framework for Large Language Model Fine-Tuning","created":"2023-12-25","cited_by_count":11,"area":null},{"id":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2310.16538","title":"FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2405.11916","title":"Information Leakage from Embedding in Large Language Models","created":"2024-05-20","cited_by_count":10,"area":null},{"id":"2408.11749","title":"Against All Odds: Overcoming Typology, Script, and Language Confusion in Multilingual Embedding Inversion Attacks","created":"2024-08-21","cited_by_count":10,"area":"safety"},{"id":"2205.06135","title":"Fair NLP Models with Differentially Private Text Encoders","created":"2022-05-12","cited_by_count":9,"area":null},{"id":"2210.02574","title":"Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption","created":"2022-10-05","cited_by_count":9,"area":null},{"id":"2308.13904","title":"LMSanitator: Defending Prompt-Tuning Against Task-Agnostic Backdoors","created":"2023-08-26","cited_by_count":9,"area":"safety"},{"id":"2312.17342","title":"SentinelLMs: Encrypted Input Adaptation and Fine-tuning of Language Models for Private and Secure Inference","created":"2023-12-28","cited_by_count":9,"area":null},{"id":"2404.02462","title":"A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability","created":"2024-04-03","cited_by_count":9,"area":"safety"},{"id":"2506.17090","title":"Better Language Model Inversion by Compactly Representing Next-Token Distributions","created":"2025-06-20","cited_by_count":9,"area":null},{"id":"2105.10909","title":"Killing One Bird with Two Stones: Model Extraction and Attribute Inference Attacks against BERT-based APIs","created":"2021-05-23","cited_by_count":8,"area":null},{"id":"2210.11049","title":"How Does a Deep Learning Model Architecture Impact Its Privacy? A Comprehensive Study of Privacy Attacks on CNNs and Transformers","created":"2022-10-20","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":"2411.05034","title":"Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization","created":"2024-11-06","cited_by_count":8,"area":null},{"id":"2504.00147","title":"Universal Zero-shot Embedding Inversion","created":"2025-03-31","cited_by_count":8,"area":null},{"id":"2304.02932","title":"Quantifying and Defending against Privacy Threats on Federated Knowledge Graph Embedding","created":"2023-04-06","cited_by_count":7,"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":"2402.08227","title":"Privacy-Preserving Language Model Inference with Instance Obfuscation","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2410.13237","title":"Large Language Models are Easily Confused: A Quantitative Metric, Security Implications and Typological Analysis","created":"2024-10-17","cited_by_count":7,"area":null},{"id":"2511.06571","title":"Rep2Text: Decoding Full Text from a Single LLM Token Representation","created":"2025-11-09","cited_by_count":7,"area":null},{"id":"2107.01806","title":"Evaluating the Cybersecurity Risk of Real World, Machine Learning Production Systems","created":"2021-07-05","cited_by_count":6,"area":null}],"next_cursor":"100"}