Agentic Backdoors via Pretraining Poisoning
Agentic Backdoors via Pretraining Poisoning (arxiv.org)
要約
大規模言語モデル（LLM）の事前学習データに攻撃者が悪意のあるコンテンツを仕込むことで、エージェントにリモートコード実行のバックドアを埋め込むことが可能であることが示されました。Qwen3モデルを用いた実験では、事前学習コーパスのわずか0.1%を汚染するだけで、トリガーが存在する場合に攻撃者が指定したコマンドを実行するエージェントを導入できることが確認されました。モデルの規模が大きくなるほど攻撃成功率（ASR）は向上し、4Bモデルでは92%に達しました。
全文翻訳
Computer Science > Cryptography and Security
arXiv:2610.37741 (cs)
[Submitted on 27 Oct 2026]
Title: Agentic Backdoors via Pretraining Poisoning
Authors: Xinyan Hu, Pingbang Hu, Chloe Loughridge, Xuanli He, Nicholas Carlini, Matthew Jagielski, Javier Rando, Yiming Zhang
View a PDF of the paper titled Agentic Backdoors via Pretraining Poisoning, by Xinyan Hu and 7 other authors
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.
| Subjects: | Cryptography and Security (cs.CR); Computation and Language (cs.CL); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.37741 [cs.CR] |
| (or arXiv:2610.37741v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2610.37741 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xinyan Hu [view email]
[v1] Tue, 27 Oct 2026 16:53:52 UTC (518 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Agentic Backdoors via Pretraining Poisoning, by Xinyan Hu and 7 other authors
［画像: license icon］ view license
Additional Features
Current browse context:
cs.CR
Change to browse by:
References & Citations
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?)