Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout

Computer Science > Cryptography and Security [Submitted on 10 Apr 2026] Conversations Risk Detection LLMs in Financial Agents via Multi-Stage Generative Rollout Xiaotong Jiang, Jun Wu With the rapid adoption of large language models (LLMs) in financial service scenarios, dialogue security detection under high regulatory risk presents significant challenges. Existing methods mainly rely on single-dimensional semantic judgments or fixed rules, making them inadequate for handling multi-turn semantic evolution and complex regulatory clauses; moreover, they lack models specifically designed for financial security detection. To address these issues, this paper proposes FinSec, a four-tier security detection framework for financial agent. FinSec enables structured, interpretable, and end-to-end identification of actual financial risks, incorporating suspicious behavior pattern analysis, delayed risk and adversarial inference, semantic security analysis, and integrated risk-based decision-making. Notably, FinSec significantly enhances the robustness of high-risk dialogue detection while maintaining model utility. Experimental results demonstrate FinSec's leading performance. In terms of overall detection capability, FinSec achieves an F1 score of 90.13%, improving upon baseline models by 6--14 percentage points; its ASR is reduced to 9.09%, markedly lowering the probability of unsafe outputs; and the AUPRC increases to 0.9189 -- an approximate 9.7% gain over general frameworks. Additionally, in balancing utility and safety, FinSec obtains a composite score of 0.9098, delivering robust and efficient protection for financial agent dialogues. Subjects: Cryptography and Security (cs.CR); Computational Engineering, Finance, and Science (cs.CE) Cite as: arXiv:2604.09056 [cs.CR]   (or arXiv:2604.09056v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2604.09056 Focus to learn more Submission history From: Xiaotong Jiang [view email] [v1] Fri, 10 Apr 2026 07:29:39 UTC (5,549 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.CE References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)