arXiv AI
Jul 14
PromptGraph: Graph-Guided Prompt Sanitization for Balancing Privacy and Utility in LLM Inference
arXiv:2607. 10709v1 Announce Type: cross Abstract: Large Language Model (LLM) services introduce a fundamental privacy challenge.
SharedRequest: Privacy-Preserving Model-Agnostic Inference for Large Language Models
arXiv:2606. 05004v1 Announce Type: cross Abstract: With the widespread deployment of public large language models (LLMs) such as ChatGPT, protecting user prompt privacy has become an increasingly critical issue.
Related stories
arXiv Computation and Language
Sep 22
LLMs as Linguistic Chameleons: Decoupling Semantics and Structure for Privacy-Preserving Communication
arXiv:2609.23193v1 Announce Type: cross Abstract: As Large Language Model (LLM) APIs become increasingly integrated into privacy-sensitive workflows, ensuring inference-time privacy without compromis...
arXiv Machine Learning
Aug 4
Defending Membership Inference Attacks via Privacy-aware Sparsity Tuning
arXiv:2410. 06814v2 Announce Type: replace Abstract: Over-parameterized models are typically vulnerable to membership inference attacks, which aim to determine whether a specific sample is included in the training of a given model.
arXiv AI
Jun 24
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
arXiv:2606. 24623v1 Announce Type: cross Abstract: Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prompts.
arXiv Machine Learning
Jul 21
Gradient-Free Privacy Leakage in Federated Language Models through Selective Weight Tampering
arXiv:2310. 16152v5 Announce Type: replace-cross Abstract: Federated learning (FL) has become a key component in various language modeling applications such as machine translation, next-word prediction, and medical record analysis.
arXiv Machine Learning
Jun 9
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
arXiv:2606. 09401v1 Announce Type: new Abstract: Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees.
arXiv AI
Aug 17
P2Skill: Privacy Preserving Skill Distillation for Cloud-Local LLM Inference Systems
arXiv:2608. 14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on personal devices.
arXiv AI
Aug 11
From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
arXiv:2602. 24210v3 Announce Type: replace-cross Abstract: Large reasoning models (LRMs) produce reasoning traces (RTs) that often contain sensitive information.
arXiv AI
Jul 22
Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
arXiv:2606. 16952v2 Announce Type: replace-cross Abstract: The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets.
arXiv AI
Sep 12
Demystifying the Privacy-Utility Trade-off in LLM Interactions
The paper investigates how privacy-preserving sanitization of user context in large language model (LLM) interactions affects downstream performance. It identifies three mechanisms—Context‑Dependent Utility, Strategic Adaptation, and Combinatorial Interplay—that explain when and how to sanitize data. Based on these insights, the authors propose an intent‑driven local protection framework using a lightweight model (Veilmind‑4B) to dynamically extract, sanitize, and restore context, achieving lower privacy leakage while maintaining higher utility than existing baselines.
arXiv AI
Sep 4
Privacy-Preserving Heterogeneous Multi-LLM Federated Inference for Cognitive Diagnosis
The paper introduces a federated inference framework that enables multiple commercial large language model (LLM) APIs—such as LLaMA‑3.3‑70B, GPT‑4o‑mini, and Claude‑3‑Haiku—to collaborate on cognitive diagnosis tasks without accessing raw student data or proprietary model internals. Each entity’s predictions are perturbed with Laplace noise to provide epsilon‑local differential privacy, and a residual‑based aggregation scheme mitigates model heterogeneity. Experiments on three educational benchmarks demonstrate strong privacy guarantees with minimal accuracy loss, confirming the framework’s practical usability and cross‑domain generalizability.
arXiv AI
Jun 15
From Prompts to Responses: Dual-Sided Data Leakage and Defense in Split Large Language Models
arXiv:2606. 14210v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in privacy-sensitive domains, where users must balance the risk of data exposure through external APIs against the high computational cost of local deployment.