arXiv Machine Learning June 2, 2026 By Naci Cankaya

Bit-Exact AI Inference Verification Without Performance Tradeoffs

Read the original on arXiv Machine Learning →

arXiv:2606. 00279v1 Announce Type: cross Abstract: Verifying claims about AI workloads is a pre- requisite for credible AI governance of covert adversaries (who comply with monitoring only when detection likelihood is high), yet the ap- parent non-determinism of GPU floating-point arithmetic forces auditors to accept approximate output matches.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

llms

arXiv AI

Jun 9

TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks

arXiv:2510. 16028v4 Announce Type: replace-cross Abstract: Neural networks increasingly run on hardware outside the user's control (cloud GPUs, inference marketplaces).

By Jianzhu Yao, Hongxu Su, Taobo Liao, Zerui Cheng, Huan Zhang, Xuechao Wang, Pramod Viswanath

llms rag diffusion efficiency safety

arXiv Machine Learning

Jun 18

Detecting Hidden ML Training With Zero-Overhead Telemetry

arXiv:2606. 19262v1 Announce Type: new Abstract: Hardware-enabled monitoring of GPU workloads underpins many proposals for AI compute governance, but if developers can defeat monitoring mechanisms, such schemes are unworkable.

By Robi Rahman, Sabiha Tajdari

safety

arXiv AI

Jun 9

FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing

arXiv:2606. 09551v1 Announce Type: cross Abstract: Two-server secure inference allows a client to query a hosted large language model (LLM) without revealing prompts or embeddings.

By Yuhan Ma, Yong Li, Stefan Schmid

llms rag benchmarks

arXiv Machine Learning

Jul 23

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

arXiv:2603. 07466v2 Announce Type: replace-cross Abstract: Cloud-based infrastructure has become the dominant platform for deploying large models, particularly large language models (LLMs).

By Heng Jin, Chaoyu Zhang, Hexuan Yu, Shanghao Shi, Ning Zhang, Y. Thomas Hou, Wenjing Lou

llms fine-tuning

arXiv Machine Learning

Jun 19

FloatDoor: Platform-Triggered Backdoors in LLMs

arXiv:2606. 19535v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts.

By Nils Loose, Jonas Sander, Felix M\"achtle, Thomas Eisenbarth

llms fine-tuning

arXiv AI

Aug 3

MOSAIC: Masked Outsourcing of Secure AI Computations

arXiv:2607. 29221v1 Announce Type: cross Abstract: We address the challenge of securely and efficiently outsourcing AI computations from a trusted but computationally weak client to an untrusted but powerful server, in the setting where the client holds both the input and the model, and the server must learn neither.

By James Hsin-yu Chiang, Sheila Zingg, Kari Kostiainen, Srdjan Capkun

llms efficiency benchmarks

Related stories

TAO: Tolerance-Aware Optimistic Verification for Floating-Point Neural Networks

Detecting Hidden ML Training With Zero-Overhead Telemetry

FuseFSS: Efficient Secure LLM Inference with Function Secret Sharing

Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI

FloatDoor: Platform-Triggered Backdoors in LLMs

MOSAIC: Masked Outsourcing of Secure AI Computations