[2607.20723] Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Cryptography and Security

arXiv:2607.20723 (cs)

[Submitted on 22 Jul 2026]

Title:Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing

Authors:Sadegh Majidi, Niloofar Mireshghallah, Kazem Taram<br>View a PDF of the paper titled Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing, by Sadegh Majidi and 2 other authors

View PDF<br>HTML (experimental)

Abstract:This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. LeakyLMs is the first to demonstrate that key model and deployment details can be inferred using only token generation timing, even when interacting through remote APIs. LeakyLMs introduces two core attacks. The first attack targets inference optimizations and deployment strategies. For example, our attack detects whether a provider uses speculative decoding, a widely deployed inference-time optimization, and further identifies the context length of the draft model used in the pipeline. Our measurements show that Google Gemini Flash 2.5 uses speculative decoding with a draft context window of approximately 128K tokens. The second attack recovers key architectural properties, including the number of transformer layers, hidden dimension size, and number of attention heads. To achieve this, LeakyLMs builds a detailed and accurate model of token-generation timing on modern NVIDIA GPUs, characterizing how latency scales with model configuration and hardware parameters. The attack then performs a search over the architecture space using this timing model. In experiments with Llama models, the near-correct architectural configuration appears in the top-10 guesses more than 90% of the time.

Subjects:

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

Cite as:<br>arXiv:2607.20723 [cs.CR]

(or<br>arXiv:2607.20723v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2607.20723

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Sadegh Majidi [view email]<br>[v1]<br>Wed, 22 Jul 2026 20:51:28 UTC (3,819 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Leaky Language Models: Stealing Architecture and Inference Optimizations via Per-Token Timing, by Sadegh Majidi and 2 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CR

next >

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

Change to browse by:

cs<br>cs.LG

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?)

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