Language Models Can Autonomously Hack and Self-Replicate

Computer Science > Cryptography and Security [Submitted on 7 May 2026] Language Models Can Autonomously Hack and Self-Replicate Alena Air, Reworr, Nikolaj Kotov, Dmitrii Volkov, John Steidley, Jeffrey Ladish We demonstrate that language models can autonomously replicate their weights and harness across a network by exploiting vulnerable hosts. The agent independently finds and exploits a web-application vulnerability, extracts credentials, and deploys an inference server with a copy of its harness and prompt on the compromised host. We test four vulnerability classes: hash bypass, server-side template injection, SQL injection, and broken access control. Qwen3.5-122B-A10B succeeds in 6-19% of attempts, and the smaller Qwen3.6-27B reaches 33% on a single A100. This already matches the current-generation GPT-5.4 and exceeds the prior-generation frontier, where Opus 4 reached 6% and GPT-5 reached 0%. Replicating Qwen weights, frontier models reach 81% (Opus 4.6) and 33% (GPT-5.4). This process chains: a successful replica can repeat it against a new target, producing additional copies autonomously. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2605.06760 [cs.CR]   (or arXiv:2605.06760v1 [cs.CR] for this version)   https://doi.org/10.48550/arXiv.2605.06760 Focus to learn more Submission history From: Dmitrii Volkov [view email] [v1] Thu, 7 May 2026 17:09:36 UTC (657 KB) Access Paper: view license Current browse context: cs.CR < prev   |   next > new | recent | 2026-05 Change to browse by: cs 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?)