预填充推理通道：针对推理 LLM 的输出前缀攻击

Computer Science > Cryptography and Security arXiv:2609.29775 (cs) [Submitted on 24 Sep 2026] Title:Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs Authors:Lukáš Brůna, Robert Bridges, Adam Ek View a PDF of the paper titled Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs, by Luk\'a\v{s} Br\r{u}na and 2 other authors View PDF HTML (experimental) Abstract:Large Language Models (LLMs) consume and produce a single sequence of text; hence, if text can be added to the beginning of the LLM's response, i.e., an output prefix, then all subsequent tokens will be conditioned on it. This output-prefix attack technique is a cheap black-box prompt injection. Prior work has shown this type of attack can reliably jailbreak non-reasoning models. Most reasoning models add an intermediate scratchpad reasoning step before the assistant's final response. The ability to edit this reasoning channel is exposed by some APIs and attack vectors can be leveraged for reasoning injection attacks. We present the first systematic, controlled study that isolates the scratchpad reasoning channel as an output-prefix attack vector, and the first to compare reasoning-only, output-prefix-only and reasoning-plus-output-prefix attacks across both exposed- and hidden-reasoning models. Using a factorial design of 3 prefix types $\times$ 2 reasoning injections over $1{,}800$ test cases drawn from AdvBench, we attack three 2026-era frontier models Gemini 3 Flash Preview, DeepSeek V4 Flash, and Claude Haiku 4.5. We find that injecting malicious reasoning alone is essentially inert ($\approx0\%$ attack success), but injecting the same reasoning together with a trivial output prefix raises the attack success rate to as high as $99\%$ for some models. For this type of attack we find that contextual prefixes work better than static prefixes; and that susceptibility is dependent on the model. Subjects: Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) Cite as: arXiv:2609.29775 [cs.CR] (or arXiv:2609.29775v1 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2609.29775 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Lukáš Brůna [view email] [v1] Thu, 24 Sep 2026 13:18:21 UTC (1,046 KB) Full-text links: Access Paper: View a PDF of the paper titled Prefilling the Reasoning Channel: Output-Prefix Attacks on Reasoning LLMs, by Luk\'a\v{s} Br\r{u}na and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR new | recent | 2026-09 Change to browse by: cs cs.AI References & Citations NASA ADS Google 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?)