LLM 作为跨链桥验证器:评估 Solana 上的源码级与交易级攻击检测
LLMs as Validators for Cross-Chain Bridges: Evaluating Source-Level and Transaction-Level Attack Detection on Solana
AI 导读
一项 arXiv 研究在本地 Solana 验证器上实现 Rust lock-and-mint 跨链桥及四种可利用变体,评估五个开源权重模型的六种配置在 16,800 次响应中诊断跨链桥漏洞的能力。结果显示,无注释时模型仅诊断出 24% 的漏洞源码输入,且常误报安全桥;交易级诊断在 missing-signer 场景较高,其余三个场景平均仅 6%;加入原始注释后源码诊断率升至 60%。
正文 · 原文
Abstract:Cross-chain bridges have suffered substantial asset losses due to vulnerabilities in their on-chain programs. On Solana, missing validation checks can enable exploits even when the underlying blockchain operates correctly. The ability of large language models (LLMs) to diagnose these flaws from source code or transaction records, rather than merely raise alarms, remains insufficiently understood. We implement a native Rust lock-and-mint bridge on a local Solana validator with four exploitable variants: two model flaws from the Cashio and Wormhole incidents, while the other two represent vulnerability classes documented in Solana security audits. Paired vulnerable and secure programs, together with successful attacks, benign sessions, and blocked attempts, allow us to distinguish correct diagnoses from unsupported alarms. We evaluate six configurations of five open-weight models across 16,800 responses, compare source inputs with and without comments, and grade 7,200 answers on vulnerable inputs using two blinded LLM graders. The results reveal substantial differences across conditions: without comments, models diagnose 24% of vulnerable source inputs while frequently flagging the secure bridge. Transaction diagnosis is high for the missing-signer scenario but averages 6% across the other three scenarios. Original comments, some of which describe the flaw, increase source diagnosis to 60%. These findings highlight the importance of distinguishing correct vulnerability diagnoses from unsupported alarms in bridge security review.
| Comments: | 11 pages, 5 figures, 5 tables, ACM Trust 2027 |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.21777 [cs.CR] |
| (or arXiv:2611.21777v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21777 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ishraq Samiha [view email]
[v1]
Mon, 16 Nov 2026 19:05:56 UTC (519 KB)
来源:arXiv cs.AI · arxiv.org