{"total":56,"rows":[{"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":"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":"2311.09447","title":"How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities","created":"2023-11-15","cited_by_count":33,"area":null},{"id":"2310.09130","title":"Split-and-Denoise: Protect large language model inference with local differential privacy","created":"2023-10-13","cited_by_count":32,"area":null},{"id":"2406.02958","title":"PrE-Text: Training Language Models on Private Federated Data in the Age of LLMs","created":"2024-06-05","cited_by_count":29,"area":null},{"id":"2310.09639","title":"DPZero: Private Fine-Tuning of Language Models without Backpropagation","created":"2023-10-14","cited_by_count":26,"area":null},{"id":"2404.06001","title":"Privacy Preserving Prompt Engineering: A Survey","created":"2024-04-09","cited_by_count":25,"area":null},{"id":"2402.01749","title":"Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models","created":"2024-01-30","cited_by_count":23,"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":"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":"2406.14318","title":"The Fire Thief Is Also the Keeper: Balancing Usability and Privacy in Prompts","created":"2024-06-20","cited_by_count":13,"area":null},{"id":"2405.01678","title":"1-Diffractor: Efficient and Utility-Preserving Text Obfuscation Leveraging Word-Level Metric Differential Privacy","created":"2024-05-02","cited_by_count":10,"area":null},{"id":"2511.22788","title":"PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration","created":"2025-11-27","cited_by_count":10,"area":null},{"id":"2402.05868","title":"EmojiPrompt: Generative Prompt Obfuscation for Privacy-Preserving Communication with Cloud-based LLMs","created":"2024-02-08","cited_by_count":9,"area":null},{"id":"2406.03749","title":"NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human","created":"2024-06-06","cited_by_count":8,"area":null},{"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":"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":"2403.04124","title":"Privacy-preserving Fine-tuning of Large Language Models through Flatness","created":"2024-03-07","cited_by_count":6,"area":null},{"id":"2505.17145","title":"LLM Access Shield: Domain-Specific LLM Framework for Privacy Policy Compliance","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2405.18194","title":"Delving into Differentially Private Transformer","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2505.05922","title":"Cape: Context-Aware Prompt Perturbation Mechanism with Differential Privacy","created":"2025-05-09","cited_by_count":5,"area":null},{"id":"2508.03097","title":"VFLAIR-LLM: A Comprehensive Framework and Benchmark for Split Learning of LLMs","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2512.06711","title":"Parameter-Efficient Fine-Tuning with Differential Privacy for Robust Instruction Adaptation in Large Language Models","created":"2025-12-07","cited_by_count":5,"area":null},{"id":"2401.00870","title":"ConfusionPrompt: Practical Private Inference for Online Large Language Models","created":"2023-12-30","cited_by_count":3,"area":null},{"id":"2502.15233","title":"A General Pseudonymization Framework for Cloud-Based LLMs: Replacing Privacy Information in Controlled Text Generation","created":"2025-02-21","cited_by_count":3,"area":null},{"id":"2509.20838","title":"Zero-Shot Privacy-Aware Text Rewriting via Iterative Tree Search","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2509.23459","title":"MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2601.10004","title":"SoK: Privacy-aware LLM in Healthcare: Threat Model, Privacy Techniques, Challenges and Recommendations","created":"2026-01-15","cited_by_count":3,"area":null},{"id":"2406.11087","title":"DP-MemArc: Differential Privacy Transfer Learning for Memory Efficient Language Models","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2410.13905","title":"P4GCN: Vertical Federated Social Recommendation with Privacy-Preserving Two-Party Graph Convolution Network","created":"2024-10-16","cited_by_count":2,"area":null},{"id":"2411.03730","title":"NeurIPS 2023 Competition: Privacy Preserving Federated Learning Document VQA","created":"2024-11-06","cited_by_count":2,"area":null},{"id":"2411.15831","title":"Efficient and Private: Memorisation under differentially private parameter-efficient fine-tuning in language models","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2508.17767","title":"ISACL: Internal State Analyzer for Copyrighted Training Data Leakage","created":"2025-08-25","cited_by_count":2,"area":null},{"id":"2602.11513","title":"Differentially Private and Communication Efficient Large Language Model Split Inference via Stochastic Quantization and Soft Prompt","created":"2026-02-12","cited_by_count":2,"area":null},{"id":"2603.01499","title":"Towards Privacy-Preserving LLM Inference via Covariant Obfuscation (Technical Report)","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2606.14210","title":"From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2402.11224","title":"Neural Networks with (Low-Precision) Polynomial Approximations: New Insights and Techniques for Accuracy Improvement","created":"2024-02-17","cited_by_count":1,"area":null},{"id":"2403.07283","title":"A Framework for Cost-Effective and Self-Adaptive LLM Shaking and Recovery Mechanism","created":"2024-03-12","cited_by_count":1,"area":null},{"id":"2508.10836","title":"SoK: Data Minimization in Machine Learning","created":"2025-08-14","cited_by_count":1,"area":null},{"id":"2509.06264","title":"PLRV-O: Advancing Differentially Private Deep Learning via Privacy Loss Random Variable Optimization","created":"2025-09-08","cited_by_count":1,"area":null},{"id":"2512.08809","title":"PrivTune: Efficient and Privacy-Preserving Fine-Tuning of Large Language Models via Device-Cloud Collaboration","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2604.06831","title":"Towards Privacy-Preserving Large Language Model: Text-free Inference Through Alignment and Adaptation","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2606.05004","title":"SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models","created":"2026-06-03","cited_by_count":1,"area":null},{"id":"2606.16801","title":"The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2609.09794","title":"Privacy-Preserving Split Learning for Federated LLM Fine-Tuning","created":"2026-09-09","cited_by_count":1,"area":null},{"id":"2407.00764","title":"Characterizing Stereotypical Bias from Privacy-preserving Pre-Training","created":"2024-06-30","cited_by_count":0,"area":null},{"id":"2409.11663","title":"Training with Differential Privacy: A Gradient-Preserving Noise Reduction Approach with Provable Security","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2602.23516","title":"Lap2: Revisiting Laplace DP-SGD for High Dimensions via Majorization Theory","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2606.16461","title":"Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2608.04477","title":"DeepInvert: Semi-Supervised Embedding Inversion Against Obfuscated Language Models","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.18767","title":"Gradient Mirage: Trainable yet Label-Unidentifiable Gradients in Large Language Model Split Learning","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.23382","title":"Spectrum-Aware Bounds on Invertibility for Privacy-Enhancing Instance Encoding","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.26655","title":"When Privacy Hurts Mergeability: Geometry-Aware Model Merging under Differential Privacy","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.06749","title":"A Novel Semantic Manifold Alignment Attack against Embedding-to-Embedding Obfuscation in Privacy-Preserving LLMs","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2610.04128","title":"What Gradients Add to Text Leakage in Split Language Models, Counted per Token and per Document","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13132","title":"DP-MIND: Differentially private memory-guided Long context Inference","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}