cd /news/ai-safety/privacy-leakage-from-gradients-in-sp… · home topics ai-safety article
[ARTICLE · art-122053] src=arxiv.org ↗ pub= topic=ai-safety verified=true sentiment=↓ negative

Privacy Leakage from Gradients in Split-LLM Training

A systems-security case study of a two-node split-LLM training system found that the returned gradient leaks private data, nullifying decoy defenses, with the pattern of zero gradients revealing real rows on every frame (4,096 of 4,096 per run) across nine seeds. The attack recovered about one extra token per hundred over a constant-guess baseline (+0.65 to +1.50 percentage points), while shuffled controls recovered nothing. Clipping and noising each gradient row closed the leak for about 0.01 nats of held-out cross-entropy, but the authors caution that five classes of attacks, including those accumulating observations across training steps, were never measured.

read2 min views1 publishedSep 7, 2026
Privacy Leakage from Gradients in Split-LLM Training
Image: source
  [Submitted on 3 Sep 2026]


[View PDF](/pdf/2609.04382)

[HTML (experimental)](https://arxiv.org/html/2609.04382v1)

Abstract:We present a systems-security case study of a two-node split-LLM training system whose privacy evaluation passed while leaving an observable channel untested. The Trusted Local Node (TLN) sends protected activations to the Untrusted Cloud Node (UCN), the UCN returns its output, and TLN, holding the private loss, returns the output gradient. The frame the UCN receives mixes real rows with decoys, and the loss ignores the decoys. Their gradients are exactly zero, so the pattern of zeros reveals which rows were real. We measure it with a protocol fixed in advance: a leak injected at known strength to prove the instrument can see one, a shuffled-label control to prove it does not report absent leaks, and a threshold set before the runs. Across nine seeds, the zeros identified the real rows on every frame, 4,096 of 4,096 per run. An attack on the frame contents recovered about one extra token per hundred over a constant-guess baseline (+0.65 to +1.50 percentage points); the shuffled controls recovered nothing. A second set of runs repeated this on a configuration that keeps model quality within budget, so the finding is not confined to a setting nobody would deploy. On both datasets, every such run passed the forward-channel privacy check and the quality check, yet failed that same check once the returned gradient was included. Clipping and noising each row of the gradient closed the leak for about 0.01 nats of held-out cross-entropy. The system is not thereby safe: five classes of attack, including those accumulating observations across training steps, were never measured.

Current browse context:

cs.CR

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?) 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?) Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?) 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 #ai-safety 4 stories · sorted by recency
── more on @trusted local node 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/privacy-leakage-from…] indexed:0 read:2min 2026-09-07 ·