[2607.28884] Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference

Skip to main content

Search arXiv

Press Enter to search · Advanced search

-->

Computer Science > Cryptography and Security

arXiv:2607.28884 (cs)

[Submitted on 30 Jul 2026]

Title:Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference

Authors:Chen Gong, Beijie Liu, Mengyuan Li<br>View a PDF of the paper titled Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference, by Chen Gong and Beijie Liu and Mengyuan Li

View PDF<br>HTML (experimental)

Abstract:As large language models (LLMs) grow in scale and are predominantly served from remote platforms, verifying faithful inference execution becomes critical (i.e., ensuring that a provider actually executes the advertised model and computational workload rather than a tampered or downsized variant). Zero-knowledge (ZK) LLM inference offers an appealing approach. It promises public verifiability and delivers per-instance guarantees of equational correctness by proving that an output is consistent with executing a public architecture under committed, private weights. Though, we show that it does not bind the effort expended to produce the output. In this paper, we formalize this overlooked effort gap and introduce the Hollow-LLM Attack, in which a dishonest provider retains the declared architecture and parameter count but embeds ghost weights whose algebraic structure collapses effective computation. These witnesses satisfy the verification circuit and yield valid proofs, even though the dishonest model owner, who serves as the prover, performs computation commensurate with a much smaller model than the declared public architecture. This creates a profitable equilibrium in which providers deliver provably correct outputs at small-model cost while overclaiming model size. Accordingly, we characterize concrete families of ghost weights that compose with standard transformer blocks and show that such hollow deployments substantially reduce serving cost with zero quality loss under the same verification circuit. These findings underscore that proof of correct inference is not proof of large-model execution and necessitate additional protections to bind correctness to verifiable computational work.

Comments:<br>Accepted to the 2026 IEEE Symposium on Security and Privacy (S&P 2026)

Subjects:

Cryptography and Security (cs.CR)

Cite as:<br>arXiv:2607.28884 [cs.CR]

(or<br>arXiv:2607.28884v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2607.28884

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Related DOI:

https://doi.org/10.1109/SP63933.2026.00258

Focus to learn more

DOI(s) linking to related resources

Submission history<br>From: Chen Gong [view email]<br>[v1]<br>Thu, 30 Jul 2026 23:00:59 UTC (2,263 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled Hollow-LLM Attack: Computationally Trivial Weights in Zero-Knowledge Verification of LLM Inference, by Chen Gong and Beijie Liu and Mengyuan Li<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

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...