Integrity of peer-to-peer distributed LLM inference under malicious nodes

• URL: http://arxiv.org/abs/2607.19490v1
• Date: Tue, 21 Jul 2026 18:08:43 GMT
• Title: Integrity of peer-to-peer distributed LLM inference under malicious nodes
• Abstract summary: Peer-to-peer distributed inference executes a Large Language Model (LLM) on pooled consumer hardware by spreading its layers across many nodes.<n>Any party can tamper with the output of its layers to corrupt the end result.<n>We propose a method that checks the output integrity by measuring the variation in the activations that each node passes to the next.
• Score: 1.6328866317851185
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Peer-to-peer distributed inference executes a Large Language Model (LLM) on pooled consumer hardware by spreading its layers across many nodes. Every request passes through nodes that are owned and controlled by multiple independent parties. However, in this setting, any party can tamper with the output of its layers to corrupt the end result. Recomputing the forward pass on trusted hardware can catch this, but it introduces additional computational cost. The scientific literature includes several prior integrity-checking approaches, such as known-answer traps for image classifiers and cryptographic commitments. However, these solutions test only the exact correctness and do not account for the ordinary variation that may arise between benign nodes. In this paper, we propose a method that checks the output integrity by measuring the variation in the activations that each node passes to the next. A peer who wants to use the network selects a small set of secret canary inputs whose correct activations are known in advance and mixes them into regular traffic. Because the peers cannot tell a canary from a real query, any tampering node corrupts them as well. The deviation from the known reference then reveals malicious activity: benign nodes exhibit only minor variation from hardware-induced noise, whereas tampered nodes deviate far more. We treat the identification of malicious nodes as a probabilistic test that separates two drift distributions, without relying on a fixed threshold. We study 408 configurations with metrics and success criteria fixed before any experiment ran; the detector reaches AUROC 1.0, correctly ranking the malicious shard above every benign shard on every canary in every configuration.

Related papers

• Correction and Corruption: A Two-Rate View of Error Flow in LLM Protocols [51.56484100374058]
  We propose a paired-outcome measurement interface for auditing a single protocol step on exact-match tasks.<n>For each instance, the interface records a baseline correctness bit and a post-step correctness bit.<n>These rates predict accuracy changes and define a reusable empirical interface testable across seeds, mixtures, and pipelines.
  arXiv  Detail & Related papers  (2026-04-20T13:25:40Z)
• HadAgent: Harness-Aware Decentralized Agentic AI Serving with Proof-of-Inference Blockchain Consensus [4.693243537924961]
  We present HadAgent, a decentralized agentic AI serving system that replaces hash-based mining with Proof-of-Inference (PoI)<n>HadAgent organizes validated records into a three-lane block body with dedicated DATA, MODEL, and PROOF channels.<n>Experiments on a prototype implementation demonstrate 100% detection rate and 0% false positive rate for tampered records.
  arXiv  Detail & Related papers  (2026-04-15T14:46:29Z)
• GroupEnsemble: Efficient Uncertainty Estimation for DETR-based Object Detection [10.241307426902178]
  GroupEnsemble is an efficient and effective uncertainty estimation method for DETR-like models.<n>We validated our method under autonomous driving scenes and common daily scenes using the Cityscapes and COCO datasets.<n>The results show that a hybrid approach combining MC-Dropout and GroupEnsemble outperforms Deep Ensembles on several metrics at a fraction of the cost.
  arXiv  Detail & Related papers  (2026-03-02T13:26:40Z)
• Benchmarking Fraud Detectors on Private Graph Data [70.4654745317714]
  Currently, many types of fraud are managed in part by automated detection algorithms that operate over graphs.<n>We consider the scenario where a data holder wishes to outsource development of fraud detectors to third parties.<n>Third parties submit their fraud detectors to the data holder, who evaluates these algorithms on a private dataset and then publicly communicates the results.<n>We propose a realistic privacy attack on this system that allows an adversary to de-anonymize individuals' data based only on the evaluation results.
  arXiv  Detail & Related papers  (2025-07-30T03:20:15Z)
• FLoW3 -- Web3 Empowered Federated Learning [0.0]
  Federated Learning is susceptible to various kinds of attacks like Data Poisoning, Model Poisoning and Man in the Middle attack. validation is done through consensus by employing Novelty Detection and Snowball protocol. System is realized by implementing in python and Foundry for smart contract development.
  arXiv  Detail & Related papers  (2023-12-09T04:05:07Z)
• RecAGT: Shard Testable Codes with Adaptive Group Testing for Malicious Nodes Identification in Sharding Permissioned Blockchain [8.178194928962311]
  We propose RecAGT, a novel identification scheme aimed at reducing communication overhead and identifying potential malicious nodes. First, shard testable codes are designed to encode the original data in case of a leak of confidential data. Second, a new identity proof protocol is presented as evidence against malicious behavior. Third, adaptive group testing is chosen to identify malicious nodes.
  arXiv  Detail & Related papers  (2023-11-05T07:43:48Z)
• Transaction Fraud Detection via an Adaptive Graph Neural Network [64.9428588496749]
  We propose an Adaptive Sampling and Aggregation-based Graph Neural Network (ASA-GNN) that learns discriminative representations to improve the performance of transaction fraud detection. A neighbor sampling strategy is performed to filter noisy nodes and supplement information for fraudulent nodes. Experiments on three real financial datasets demonstrate that the proposed method ASA-GNN outperforms state-of-the-art ones.
  arXiv  Detail & Related papers  (2023-07-11T07:48:39Z)
• Collective Robustness Certificates: Exploiting Interdependence in Graph Neural Networks [71.78900818931847]
  In tasks like node classification, image segmentation, and named-entity recognition we have a classifier that simultaneously outputs multiple predictions. Existing adversarial robustness certificates consider each prediction independently and are thus overly pessimistic for such tasks. We propose the first collective robustness certificate which computes the number of predictions that are simultaneously guaranteed to remain stable under perturbation.
  arXiv  Detail & Related papers  (2023-02-06T14:46:51Z)
• QuTE: decentralized multiple testing on sensor networks with false discovery rate control [93.1040521878626]
  This paper designs methods for decentralized multiple hypothesis testing on graphs equipped with provable guarantees on the false discovery rate (FDR)<n>We consider the setting where distinct agents reside on the nodes of an undirected graph, and each agent possesses p-values corresponding to one or more hypotheses local to its node.<n>Each agent must individually decide whether to reject one or more of its local hypotheses by only communicating with its neighbors, with the joint aim that the global FDR over the entire graph must be controlled at a predefined level.
  arXiv  Detail & Related papers  (2022-10-09T19:48:39Z)
• GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation [70.75100533512021]
  In this paper, we formulate the label uncertainty problem as the diversity of potentially plausible bounding boxes of objects. We propose GLENet, a generative framework adapted from conditional variational autoencoders, to model the one-to-many relationship between a typical 3D object and its potential ground-truth bounding boxes with latent variables. The label uncertainty generated by GLENet is a plug-and-play module and can be conveniently integrated into existing deep 3D detectors.
  arXiv  Detail & Related papers  (2022-07-06T06:26:17Z)

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.