邊緣離線生成式 AI 的信任機制:連線狀態框架及 Raspberry Pi 5 實證研究
Trust Mechanisms for Offline Generative AI at the Edge: A Connectivity-Regime Framework and an Empirical Study on a Raspberry Pi 5
研究提出 C0-C4 連線狀態框架及推理時信任機制分類,並在 Raspberry Pi 5 上評估本地檢索增強生成,測試三種 Qwen2.5 模型規模。檢索分數閘門識別知識缺口的 AUROC 為 0.97,但對主題內無法回答的問題表現較差,AUROC 為 0.68。有效簽署的污染知識包仍可通過所有檢查,令 30 條原本答對的問題全數答錯,當中 14 條返回注入答案;所測機制均不能確立證據真偽。
Published on Oct 24
Authors:
Abstract
Local retrieval-augmented generation on edge devices using signed knowledge packs and output validators improves efficiency but remains vulnerable to poisoned updates and cannot guarantee evidence truth.
Generative AI and large language models (LLMs) are moving into the Internet of Things, yet most deployments assume cloud connectivity, and many IoT settings have intermittent, restricted, or no connectivity. We propose a connectivity-regime framework (C0-C4), a taxonomy of inference-time trust mechanisms, and signed, versioned knowledge packs as the update channel for disconnected regimes, and evaluate them on a Raspberry Pi 5 running fully local retrieval-augmented generation under network isolation, with three Qwen2.5 model sizes, three context sizes, and 300 SQuAD 2.0 questions. An empirically calibrated retrieval-score gate detects knowledge gaps almost perfectly (AUROC 0.97) but in-topic unanswerable questions poorly (0.68). A deterministic output validator converts malformed outputs into explicit abstentions with no observed loss of correct answers, while the NLI-based verifier we tested adds little; for the 7B model, 96% of substantive answers to unanswerable-labelled questions match normalized spans of the retrieved passages. A 3B model achieves the same gold-answer containment rate as a 7B model at less than half the latency and estimated energy, although the 7B model far more often exceeds a token-F1 threshold of 0.5; five retrieved passages lower correctness from 75% to 52% compared with three. Verifying a signed pack takes about 4.5 ms versus about 29 min for embedding its passages on the device; signature and hash checks alone accept six of nine tested update attacks that layered verification rejects. Yet a validly signed poisoned pack passes every pack check: on 30 previously correct questions, correct answers drop to zero and 14 return the injected answer. None of the mechanisms we evaluated establishes the truth of the evidence. We release code and data.
View arXiv page View PDF Project page GitHub 0 Add to collection
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.33732 in a model README.md to link it from this page.
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.33732 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.33732 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co