cd /news/large-language-models/leaky-language-models-stealing-archi… · home topics large-language-models article
[ARTICLE · art-71582] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=↓ negative

Leaky Language Models: Stealing Architecture and Inference Optimizations

Researchers have developed LeakyLMs, a set of attacks that infer proprietary model architecture and deployment details from production language models using only token generation timing. The attacks can detect whether a provider uses speculative decoding, identifying Google Gemini Flash 2.5's draft context window as approximately 128K tokens, and recover architectural properties such as the number of transformer layers, hidden dimension size, and attention heads. In experiments with Llama models, the near-correct architectural configuration appears in the top-10 guesses more than 90% of the time.

read2 min views1 publishedJul 24, 2026
Leaky Language Models: Stealing Architecture and Inference Optimizations
Image: source
[Submitted on 22 Jul 2026]


[View PDF](/pdf/2607.20723)

[HTML (experimental)](https://arxiv.org/html/2607.20723v1)

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.

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?)# Code, Data and Media Associated with this Article alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?)# Demos Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?)# 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.

── more in #large-language-models 4 stories · sorted by recency
── more on @leakylms 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/leaky-language-model…] indexed:0 read:2min 2026-07-24 ·