Privacy Foundations for Multi-Institutional Scientific Artificial Intelligence

arXiv:2609.39787 · cs.CR · Submitted 2026-09-30 · Read on arXiv

cs.CR

Submitted: 2026-09-30

Updated: 2026-09-30

Terminology

• Provenance — 15× in this paper · explained in 3 episodes
• Aggregation — 13× in this paper · explained in 1 episode
• Federated Learning — 8× in this paper · explained in 14 episodes
• Benchmark — 7× in this paper · explained in 2 episodes
• Trace — 7× in this paper · explained in 2 episodes
• Differential Privacy — 6× in this paper · explained in 4 episodes
• Abstraction — 5× in this paper · explained in 1 episode
• Adaptation — 3× in this paper · explained in 1 episode
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Foundation Models (FMs) — 3× in this paper · explained in 2 episodes
• Calibration — 2× in this paper · explained in 7 episodes
• Differential Privacy (DP) — 2× in this paper · explained in 7 episodes
• Distillation — 2× in this paper · explained in 2 episodes
• Federated Learning (FL) — 2× in this paper · explained in 7 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• AI Agents — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Artificial Intelligence (AI) — 1× in this paper · explained in 2 episodes
• Decentralized Learning — 1× in this paper · explained in 2 episodes
• Differentially Private — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Scalable Cross-Facility Federated Learning for Scientific Foundation Models on Multiple Supercomputers
• LLM Dataset Inference: Did you train on my dataset?
• Confidential Computing on NVIDIA Hopper GPUs: A Performance Benchmark Study
• AgentLeak: A Benchmark for Internal-Channel Privacy Leakage in Multi-Agent LLM Systems
• Privacy Auditing with Zero (0) Training Run
• The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration

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