Agentic Backdoors via Pretraining Poisoning

A 27 October 2026 arXiv paper reports that poisoning just 0.1% of a large language model's pretraining corpus can implant a remote code execution backdoor in a deployed CLI agent, causing it to run attacker-chosen commands on the user's machine. The researchers pretrained Qwen3 models from scratch at 0.6B, 1.7B, and 4B parameters and post-trained each into a CLI agent on a clean pipeline; attack success rate rose with model scale, with the 4B model reaching roughly 92% ASR at a 0.1% poison rate and remaining positive even at a 0.0005% poison rate. The code is published at github.com/safety-research/agentic-backdoor.

Computer Science Cryptography and Security Submitted on 27 Oct 2026 Title:Agentic Backdoors via Pretraining Poisoning View PDF https://arxiv.org/pdf/2610.37741 HTML experimental https://arxiv.org/html/2610.37741v1 Abstract:Large language models are pretrained on vast, uncurated corpora scraped from the public web. This creates a security risk from attackers who plant poisoned content in the pretraining data. We show for the first time that such poisoning can plant a remote code execution backdoor in an agent, causing it to execute attacker-chosen commands on the user's machine. To measure the threat end to end, we pretrain Qwen3 models from scratch at sizes 0.6B, 1.7B, and 4B, and then post-train each into a CLI agent using a clean pipeline. Poisoning only 0.1% of the pretraining corpus with our new poison design implants the backdoor: the deployed agent executes the malicious command when the trigger is present while behaving normally on clean inputs. The attack success rate ASR increases with model scale, with the 4B model reaching roughly 92% ASR at a 0.1% poison rate and staying positive even when the poisoning rate drops to 0.0005%. Our code is available at this https URL https://github.com/safety-research/agentic-backdoor . Additional Features Current browse context: cs.CR References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender 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 https://info.arxiv.org/labs/index.html .