跨輪交互圖識別提示提取行為

Computer Science > Cryptography and Security arXiv:2610.

36295 (cs) [Submitted on 26 Oct 2026] Title:Detecting and Mitigating Query-Based System Prompt Leakage Attacks Authors:Tushar Nayan, Pratik Poudel, Qian Lou, Yuede Ji, Jason Liu, Ruimin Sun View a PDF of the paper titled Detecting and Mitigating Query-Based System Prompt Leakage Attacks, by Tushar Nayan and 5 other authors View PDF HTML (experimental) Abstract:Large Language Models (LLMs) rely on proprietary system prompts to enforce task directives, safety policies, and access controls.

These prompts are vulnerable to query-based leakage attacks, where black-box adversaries extract confidential instructions through adaptive, multi-turn interactions.Existing defenses often assess queries independently, missing malicious behavior that emerges across interactions.

We present AdvGuard, a model-agnostic framework for detecting and mitigating system prompt leakage.

AdvGuard models cross-query relationships using a bounded semantic interaction graph, statistically filters candidate components, and converts them into line graphs for graph convolutional network (GCN) classification.

This approach captures multi-hop patterns in query similarity that distinguish coordinated extraction from benign workflows.A lightweight prompt-level detector provides protection before sufficient interaction history accumulates, and the framework supports black-box LLM deployments.

In mixed-query evaluations, AdvGuard improves recall by up to 36% over the strongest baseline while maintaining a false positive rate of at most 3.4%.In multi-turn workloads, it achieves 97.23%-99.1% F1 with 100% recall.Leave-one-attack-family-out tests yield 99.98% mean recall and 99.

99% mean F1, with no observed false positives.Integrated into the adaptive PLeak and LeakAgent attack loops, AdvGuard limits exact-match leakage to 0.00-0.01 and substring-match leakage to 0.01-0.09 across evaluated victim models.

These results demonstrate robust detection of unseen attack families and substantially reduced prompt reconstruction.Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2610.36295 [cs.CR] (or arXiv:2610.36295v1 [cs.CR] for this version) https://doi.org/10.

48550/arXiv.2610.

36295 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Tushar Nayan [view email] [v1] Mon, 26 Oct 2026 21:23:10 UTC (740 KB) Full-text links: Access Paper: View a PDF of the paper titled Detecting and Mitigating Query-Based System Prompt Leakage Attacks, by Tushar Nayan and 5 other authorsView PDFHTML (experimental)TeX Source view license Additional Features Audio Summary Current browse context: cs.

CR < prev | next > new | recent | 2026-10 Change to browse by: cs cs.AI References & Citations SciXGoogle Scholar Semantic Scholar export BibTeX citation Loading...BibTeX formatted citation × loading...

Data provided by: 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 Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?

) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.

AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?

) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.Which authors of this paper are endorsers?| Disable MathJax (What is MathJax?)