Towards TEE-Certified DP: Verifiable Differentially Private Training on Legacy GPUs

arXiv:2609.20532 · cs.CR · Submitted 2026-09-17 · Read on arXiv

cs.CR

Submitted: 2026-09-17

Updated: 2026-09-17

Code: https://github.com/microsoft/dptransformers

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Verification — 102× in this paper · explained in 2 episodes
• Calibration — 64× in this paper · explained in 7 episodes
• Verifier — 41× in this paper · explained in 2 episodes
• Differential Privacy — 18× in this paper · explained in 4 episodes
• Fine-Tuning — 15× in this paper · explained in 5 episodes
• Steering — 15× in this paper · explained in 2 episodes
• Trace — 12× in this paper · explained in 2 episodes
• Aggregation — 11× in this paper · explained in 1 episode
• Differentially Private — 8× in this paper · explained in 3 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Trusted Execution Environment — 7× in this paper
• Accuracy — 5× in this paper · explained in 1 episode
• Security and Privacy — 4× in this paper
• Transformer — 4× in this paper · explained in 2 episodes
• AUC — 3× in this paper · explained in 2 episodes
• Core — 3× in this paper · explained in 2 episodes
• Differential Privacy (DP) — 3× in this paper · explained in 7 episodes
• Adam — 2× in this paper · explained in 2 episodes
• Adaptive Strategy — 2× in this paper · explained in 1 episode
• Computational overhead — 2× in this paper · explained in 2 episodes
• Federated Learning — 2× in this paper · explained in 14 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• Clustering — 1× in this paper · explained in 2 episodes
• Convolutional Neural Networks (CNNs) — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Multi-Genre Natural Language Inference — 1× in this paper
• Provenance — 1× in this paper · explained in 4 episodes
• Query Complexity — 1× in this paper · explained in 2 episodes
• Quora Question Pairs — 1× in this paper
• Transformer Models — 1× in this paper · explained in 2 episodes
• Verifiability — 1× in this paper · explained in 2 episodes
• Zero-Knowledge Proofs (ZKPs) — 1× in this paper · explained in 3 episodes

Sources

• GuardNN: Secure Accelerator Architecture for Privacy-Preserving Deep Learning
• Verifiable Differential Privacy
• Trusting What You Cannot See: Auditable Fine-Tuning and Inference for Proprietary AI
• Auditing Apple's DifferentialPrivacy.framework: Implementation Bugs, Misconfigurations, and Practical Risks
• Imitative Membership Inference Attack
• Privacy Loss in Apple's Implementation of Differential Privacy on MacOS 10.12
• Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs