Skip to content
AI News HubLIVE
Original source2 min read

PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement

Summary

arXiv:2609.05676v1 Announce Type: new Abstract: Language models adapted on private text are often served through APIs, so privacy leakage occurs through generated outputs rather than exposed weights. Private prediction protects these releases. Methods such as PMixED incur privacy cost at each release and increasingly rely on the public model over long horizons. PAC privacy instead calibrates noise to output variability across possible secrets, adding less noise when predictions are stable. To our knowledge, PAC-private prediction has not previously been extended from classification to autoregressive generation. We construct $m=128$ overlapping worlds from the private corpus, with each record appearing in exactly $m/2$ worlds, and train one adapter per world over a frozen public model. The…

SourcearXiv Machine LearningAuthor: Mina Mirzadehsarcheshmeh, Amir Keyvan Khandani
PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 4 Sep 2026]

Title:PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement

View a PDF of the paper titled PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement, by Mina Mirzadehsarcheshmeh and 1 other authors

View PDF HTML (experimental)

Abstract:Language models adapted on private text are often served through APIs, so privacy leakage occurs through generated outputs rather than exposed weights. Private prediction protects these releases. Methods such as PMixED incur privacy cost at each release and increasingly rely on the public model over long horizons. PAC privacy instead calibrates noise to output variability across possible secrets, adding less noise when predictions are stable. To our knowledge, PAC-private prediction has not previously been extended from classification to autoregressive generation.

We construct $m=128$ overlapping worlds from the private corpus, with each record appearing in exactly $m/2$ worlds, and train one adapter per world over a frozen public model. The realized world is the secret. At each token, the public model defines a candidate set, the worlds vote, and their posterior-weighted disagreement determines the PAC noise; unanimity requires no calibration noise. We prove $I(S;Y_{1:T}) \leq I(S;H_T) \leq bT$. Our contributions are extending PAC privacy to autoregressive generation, handling adaptive self-generated contexts, and introducing coupled decoding that preserves privacy accounting while avoiding greedy degeneration.

On WikiText-103 with GPT-2-small, we retain 74% of the fine-tuning gain at a per-token budget of $2^{-32}$, while membership-inference success is bounded by 51.08% after $10^6$ tokens; posterior-entropy estimates of leakage are roughly 17% of the charged budget. Inference privacy is not content protection: even when membership advantage on a memorized canary is indistinguishable from zero, the canary is emitted at the same rate. Against PMixED under matched membership-inference bounds on the same data universe and test set, we retain 98% of non-private headroom from $10^2$ to $10^6$ tokens, versus at most 56%, with no crossover.

Subjects:

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

Cite as: arXiv:2609.05676 [cs.LG]

(or arXiv:2609.05676v1 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2609.05676

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mina Mirzadeh [view email] [v1] Fri, 4 Sep 2026 19:16:39 UTC (210 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled PAC-Private Autoregressive Generation: Calibrating Noise to Ensemble Disagreement, by Mina Mirzadehsarcheshmeh and 1 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.LG

new | recent | 2026-09

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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 (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? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.05676v1 Announce Type: new Abstract: Language models adapted on private text are often served through APIs, so privacy leakage occurs through generated outputs rather t…

Highlights and analysis are generated automatically and may contain errors. Check the original source.