CRApr 30

PAL*M: Property Attestation for Large Generative Models

arXiv:2601.1619943.11 citationsh-index: 11
Predicted impact top 46% in CR · last 90 daysOriginality Incremental advance
AI Analysis

Provides a practical framework for model providers to attest regulatory compliance to verifiers, addressing scalability gaps in prior work.

PAL*M enables property attestation for large generative models (e.g., LLMs) with <11% overhead, using confidential VMs and incremental hashing to verify training/inference properties.

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+NVIDIA H100 and evaluate it using state-of-the-art models and datasets, showing PAL*M is efficient, incurring < 11% overhead for common operations. Finally, we use the Tamarin Prover symbolic verification tool to formally model PAL*M's property attestation protocol, confirming that its security guarantees are upheld under the defined threat model.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes