PAL*M: Property Attestation for Large Generative Models

Authors: Prach Chantasantitam, Adam Ilyas Caulfield, Vasisht Duddu, Lachlan J. Gunn, N. Asokan
Published: 2026-01-22

Source: https://arxiv.org/abs/2601.16199

PDF: https://arxiv.org/pdf/2601.16199

AIにより推定されたラベル

RAG セキュリティ保証 フレームワーク

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

Machine learning property attestations allow provers (e.g., model providers or owners) to attest properties of their models/datasets to verifiers (e.g., regulators, customers), enabling accountability towards regulations and policies. But, current approaches do not support generative models or large datasets. We present PAL*M, a property attestation framework for large generative models, illustrated using large language models. PAL*M defines properties across training and inference, leverages confidential virtual machines with security-aware GPUs for coverage of CPU-GPU operations, and proposes using incremental multiset hashing over memory-mapped datasets to efficiently track their integrity. We implement PAL*M on Intel TDX and NVIDIA H100, showing it is efficient, scalable, versatile, and secure.