AVEC: Bootstrapping Privacy for Local LLMs

• URL: http://arxiv.org/abs/2509.10561v1
• Date: Wed, 10 Sep 2025 07:59:01 GMT
• Title: AVEC: Bootstrapping Privacy for Local LLMs
• Abstract summary: AVEC is a framework for bootstrapping privacy for local language models.<n>It enforces privacy at the edge with explicit verifiability for delegated queries.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This position paper presents AVEC (Adaptive Verifiable Edge Control), a framework for bootstrapping privacy for local language models by enforcing privacy at the edge with explicit verifiability for delegated queries. AVEC introduces an adaptive budgeting algorithm that allocates per-query differential privacy parameters based on sensitivity, local confidence, and historical usage, and uses verifiable transformation with on-device integrity checks. We formalize guarantees using R\'enyi differential privacy with odometer-based accounting, and establish utility ceilings, delegation-leakage bounds, and impossibility results for deterministic gating and hash-only certification. Our evaluation is simulation-based by design to study mechanism behavior and accounting; we do not claim deployment readiness or task-level utility with live LLMs. The contribution is a conceptual architecture and theoretical foundation that chart a pathway for empirical follow-up on privately bootstrapping local LLMs.

Related papers

• Phantoms and Disclosures: a Causal Framework for Auditing Synthetic Data [56.86147283213652]
  We present a customizable empirical auditing framework designed to detect and explain data disclosures.<n>Our framework introduces a mechanism to distinguish between "true disclosures"-where the system directly reproduces a user's information-and "phantom disclosures"-where the system incidentally generates a user's data.
  arXiv  Detail & Related papers  (2026-06-15T16:54:02Z)
• Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models [35.164227002323706]
  We investigate privacy risks under DP adaptations in large language models (LLMs)<n>We benchmark these risks using state-of-the-art attacks such as robust membership inference and canary data extraction.<n>We find that parameter-efficient fine-tuning methods, such as LoRA, achieve the highest empirical privacy protection for OOD data.
  arXiv  Detail & Related papers  (2026-06-08T12:21:02Z)
• LLM-CEG: Extending the Classification Error Gauge Framework for Privacy Auditing of Large Language Models [0.0]
  This paper extends the Classification Error Gauge (x-CEG) framework to privacy auditing of Large Language Models (LLMs)<n>We propose a systematic framework that employs membership inference attack (MIA) success rates as an empirical privacy gauge and model perplexity as a utility gauge.<n>A proof-of-concept prototype fine-tunes DistilGPT-2 on a synthetic clinical PII dataset under four privacy regimes using DP-SGD.
  arXiv  Detail & Related papers  (2026-04-26T16:39:37Z)
• Reinforcing privacy reasoning in LLMs via normative simulacra from fiction [1.143869785127334]
  Contextual Integrity provides a principled framework, defining privacy as the appropriate flow of information within context-relative norms.<n>We propose extracting normative simulacra from fiction novels and using them to fine-tune LLMs.<n>We evaluate on five CI-aligned benchmarks spanning distinct societal contexts.
  arXiv  Detail & Related papers  (2026-04-21T19:16:22Z)
• Differentially Private Manifold Denoising [5.0794787043927725]
  We introduce a differentially private manifold denoising framework that allows users to exploit sensitive reference datasets to correct noisy, non-private query points.<n>The framework performs rigorous privacy accounting across iterations and queries using $(varepsilon,)$-differential privacy (DP)<n> Practically, this framework brings differential privacy to manifold methods, retaining sufficient geometric signal for downstream tasks such as embedding, clustering, and visualization.
  arXiv  Detail & Related papers  (2026-04-01T14:13:59Z)
• Replacing Parameters with Preferences: Federated Alignment of Heterogeneous Vision-Language Models [63.70401095689976]
  We argue that replacing parameters with preferences represents a more scalable and privacy-preserving future.<n>We propose MoR, a federated alignment framework based on GRPO with Mixture-of-Rewards for heterogeneous VLMs.<n>MoR consistently outperforms federated alignment baselines in generalization, robustness, and cross-client adaptability.
  arXiv  Detail & Related papers  (2026-01-31T03:11:51Z)
• Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
  Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
  arXiv  Detail & Related papers  (2025-12-23T03:10:09Z)
• PRISM: Privacy-Aware Routing for Adaptive Cloud-Edge LLM Inference via Semantic Sketch Collaboration [8.776463501718737]
  We propose a context-aware framework that dynamically balances privacy and inference quality.<n>PRISM executes in four stages: (1) the edge device profiles entity-level sensitivity; (2) a soft gating module on the edge selects an execution mode - cloud, edge, or collaboration; (3) for collaborative paths, the edge applies adaptive two-layer local differential privacy based on entity risks; and (4) the cloud LLM generates a semantic sketch from the perturbed prompt.
  arXiv  Detail & Related papers  (2025-11-27T22:32:33Z)
• Tight and Practical Privacy Auditing for Differentially Private In-Context Learning [11.394805414546903]
  Large language models (LLMs) perform in-context learning (ICL) by adapting to tasks from prompt demonstrations, which in practice often contain private or proprietary data.<n>We present a tight and efficient privacy auditing framework for DP-ICL systems that runs membership inference attacks and translates their success rates into empirical privacy guarantees using Gaussian DP.<n> Experiments on standard text classification and generation benchmarks show that our empirical leakage estimates closely match theoretical DP budgets on classification tasks and are consistently lower on generation tasks due to conservative embedding-sensitivity bounds.
  arXiv  Detail & Related papers  (2025-11-17T15:39:54Z)
• Federated Learning of Quantile Inference under Local Differential Privacy [2.8462768598083823]
  We investigate learning for quantile inference under local differential privacy (LDP)<n>We propose an estimator based on local gradient descent (SGD), whose local are perturbed via a randomized mechanism with global parameters.<n>We establish normality for our estimator as well as a functional central limit theorem.
  arXiv  Detail & Related papers  (2025-09-26T02:56:39Z)
• LLMs for Resource Allocation: A Participatory Budgeting Approach to Inferring Preferences [17.089038477886486]
  Large Language Models (LLMs) are increasingly expected to handle complex decision-making tasks, but their ability to perform structured resource allocation remains underexplored.<n>We present a dual-purpose framework leveraging Participatory Budgeting (PB) both as (i) a practical setting for LLM-based resource allocation and (ii) an adaptive benchmark for evaluating their reasoning capabilities.
  arXiv  Detail & Related papers  (2025-08-08T06:45:07Z)
• Urania: Differentially Private Insights into AI Use [104.7449031243196]
  $Urania$ provides end-to-end privacy protection by leveraging DP tools such as clustering, partition selection, and histogram-based summarization.<n>Results show the framework's ability to extract meaningful conversational insights while maintaining stringent user privacy.
  arXiv  Detail & Related papers  (2025-06-05T07:00:31Z)
• Latent Factor Models Meets Instructions: Goal-conditioned Latent Factor Discovery without Task Supervision [50.45597801390757]
  Instruct-LF is a goal-oriented latent factor discovery system.<n>It integrates instruction-following ability with statistical models to handle noisy datasets.
  arXiv  Detail & Related papers  (2025-02-21T02:03:08Z)
• Assessing Correctness in LLM-Based Code Generation via Uncertainty Estimation [0.0]
  We explore uncertainty estimation as a proxy for correctness in LLM-generated code.<n>We adapt two state-of-the-art techniques from natural language generation to the domain of code generation.<n>Our findings indicate a strong correlation between the uncertainty computed through these techniques and correctness.
  arXiv  Detail & Related papers  (2025-02-17T10:03:01Z)
• LLM-Lasso: A Robust Framework for Domain-Informed Feature Selection and Regularization [59.75242204923353]
  We introduce LLM-Lasso, a framework that leverages large language models (LLMs) to guide feature selection in Lasso regression.<n>LLMs generate penalty factors for each feature, which are converted into weights for the Lasso penalty using a simple, tunable model.<n>Features identified as more relevant by the LLM receive lower penalties, increasing their likelihood of being retained in the final model.
  arXiv  Detail & Related papers  (2025-02-15T02:55:22Z)
• Communication-Efficient and Privacy-Adaptable Mechanism for Federated Learning [54.20871516148981]
  We introduce the Communication-Efficient and Privacy-Adaptable Mechanism (CEPAM)<n>CEPAM achieves communication efficiency and privacy protection simultaneously.<n>We theoretically analyze the privacy guarantee of CEPAM and investigate the trade-offs among user privacy and accuracy of CEPAM.
  arXiv  Detail & Related papers  (2025-01-21T11:16:05Z)
• Noisy Neighbors: Efficient membership inference attacks against LLMs [2.666596421430287]
  This paper introduces an efficient methodology that generates textitnoisy neighbors for a target sample by adding noise in the embedding space. Our findings demonstrate that this approach closely matches the effectiveness of employing shadow models, showing its usability in practical privacy auditing scenarios.
  arXiv  Detail & Related papers  (2024-06-24T12:02:20Z)
• Learning Robust Output Control Barrier Functions from Safe Expert Demonstrations [50.37808220291108]
  This paper addresses learning safe output feedback control laws from partial observations of expert demonstrations. We first propose robust output control barrier functions (ROCBFs) as a means to guarantee safety. We then formulate an optimization problem to learn ROCBFs from expert demonstrations that exhibit safe system behavior.
  arXiv  Detail & Related papers  (2021-11-18T23:21:00Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.