跳到正文
arXiv cs.AI· Yasir Rahman, Ishraq Samiha, Shahnewaz Karim Sakib, Anindya Bijoy Das·· 4 小时前AI 评分29

用 LLM 充当跨链桥验证器:在 Solana 上评估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

研究在本地 Solana 验证器上实现原生 Rust lock-and-mint 跨链桥,构造四个可利用变体(两个源自 Cashio 与 Wormhole 事件),用五个开放权重模型的六种配置生成 16,800 条回答,评估 LLM 能否从源码或交易记录中正确诊断漏洞而非仅报警。

正文 · 原文

View PDF HTML (experimental)

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