Statistically Undetectable Backdoors in Deep Neural Networks

sbulaev1 pts0 comments

[2607.09532] Statistically Undetectable Backdoors in Deep Neural Networks

Skip to main content

arXiv is now an independent nonprofit!<br>Learn more<br>&times;

Search arXiv

Press Enter to search &middot; Advanced search

-->

Computer Science > Machine Learning

arXiv:2607.09532 (cs)

[Submitted on 10 Jul 2026]

Title:Statistically Undetectable Backdoors in Deep Neural Networks

Authors:Andrej Bogdanov, Alon Rosen, Neekon Vafa<br>View a PDF of the paper titled Statistically Undetectable Backdoors in Deep Neural Networks, by Andrej Bogdanov and 2 other authors

View PDF<br>HTML (experimental)

Abstract:We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given the full descriptions of the models (e.g., all of the weights). The backdoor provides access to invariance-based adversarial examples for every input, mapping distant inputs to unusually close outputs. However, without the backdoor, it is provably impossible (under standard cryptographic assumptions) to generate any such adversarial examples in polynomial time. Our theoretical and preliminary empirical findings demonstrate a fundamental power asymmetry between model trainers and model users.

Comments:<br>ICML 2026

Subjects:

Machine Learning (cs.LG); Cryptography and Security (cs.CR); Machine Learning (stat.ML)

Cite as:<br>arXiv:2607.09532 [cs.LG]

(or<br>arXiv:2607.09532v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2607.09532

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Neekon Vafa [view email]<br>[v1]<br>Fri, 10 Jul 2026 15:37:32 UTC (58 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Statistically Undetectable Backdoors in Deep Neural Networks, by Andrej Bogdanov and 2 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.LG

next >

new<br>recent<br>| 2026-07

Change to browse by:

cs<br>cs.CR<br>stat<br>stat.ML

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

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?)

IArxiv recommender toggle

IArxiv Recommender<br>(What is IArxiv?)

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? |<br>Disable MathJax (What is MathJax?)

Major funding support from

toggle arxiv backdoors statistically undetectable deep

Related Articles