[2607.09532] Statistically Undetectable Backdoors in Deep Neural Networks
Skip to main content
arXiv is now an independent nonprofit!<br>Learn more<br>×
Search arXiv
Press Enter to search · 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
×
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