CORTEXA
← Browse
arxivcs.LGcs.CR2026-07-23

Agree on the Model, Verify the Inference: GKR Protocols for HND-Based Transformer Inference

Xiaolong Liang, Juanjuan Li, Rui Qin, Yisheng Lv

Outsourced Transformer inference exposes clients to model substitution and incomplete execution, while direct replay removes the computational benefit of delegation. We present GKR-HND, a registered-model protocol for verifying the polynomial backbone of Homomorphic--Nonhomomorphic Decomposition Transformers. The retained verifier checks the GKR transcript and registered-weight openings, but delegates expensive public evaluations to an assigned computation worker. Assuming an honest retained verifier and prover--worker non-collusion, the verifier accepts only when the worker's signed, request-bound response agrees with the proof claims. Experiments with pretrained HND models validate the proof path and the delegated public computation without dense-matrix replay.

View free PDFSource page

Related papers

arxivcs.LGcs.AIcs.CR2026-07-05

One Framework for All: Cross-Modal Membership Inference for Generative Models

Dayong Ye, Tainqing Zhu, Kun Gao, Junhao Liu, Yichuan Chen, Shuai Zhou, et al.

Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundamental threat is membership inference attacks (MIA), which aim to determine whether a given data point was used in a model's traini…

View free PDFSource page
arxivcs.CRcs.CLcs.LG2026-07-11

One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions

Tomas Bruckner

Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a subst…

View free PDFSource page
arxivcs.CRcs.LG2026-07-22

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

Sadegh Majidi, Niloofar Mireshghallah, Kazem Taram

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…

View free PDFSource page
arxivcs.LGcs.CR2026-07-06

Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers

Ligong Han, Kai Xu, Hao Wang, Ruijiang Gao, Han Gao, Akash Srivastava

Fully homomorphic encryption (FHE) enables computation on encrypted data, but practical encrypted Transformer inference is bottlenecked by the sequential composition of many nonlinear blocks. We study whether Structured Newton Layer Parallelism (SNLP) can make this inter-layer co…

View free PDFSource page
arxivcs.CVcs.CRcs.LG2026-07-14

Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization

Yuxin Huang, Ziming Hong, Mingming Gong, Wanyu Wang, Jing Zhang, Tongliang Liu

Recent diffusion-based video generation models have enabled high-quality personalized video customization through both tuning-based pipelines, which fine-tune a video diffusion model, and reference-based pipelines such as image-to-video generation. However, these capabilities rai…

View free PDFSource page