Reconstruction of Personally Identifiable Information from Proprietary Data in Supervised Fine-Tuned Models

arXiv:2605.12264 · cs.CR, cs.CL, cs.LG · Submitted 2026-05-12 · Read on arXiv

cs.CR, cs.CL, cs.LG

Submitted: 2026-05-12

Updated: 2026-08-25

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

Terminology

• Fine-Tuning — 34× in this paper · explained in 5 episodes
• Personally Identifiable Information — 11× in this paper
• Alignment — 7× in this paper · explained in 1 episode
• Consistency — 6× in this paper · explained in 3 episodes
• Pruning — 6× in this paper · explained in 4 episodes
• RAG — 6× in this paper · explained in 3 episodes
• Perplexity — 5× in this paper · explained in 3 episodes
• Adam — 3× in this paper · explained in 2 episodes
• Adaptation — 3× in this paper · explained in 1 episode
• California Consumer Privacy Act — 2× in this paper
• Core — 2× in this paper · explained in 2 episodes
• IEEE Symposium on Security and Privacy — 2× in this paper
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Parameter-Efficient Fine-Tuning — 2× in this paper · explained in 2 episodes
• Retrieval-Augmented Generation (RAG) — 2× in this paper · explained in 16 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accountability — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Differential Privacy — 1× in this paper · explained in 4 episodes
• Differentially Private — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Domain Adaptation — 1× in this paper · explained in 5 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In-Context Learning — 1× in this paper · explained in 4 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Membership Inference Attacks (MIAs) — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Self-distillation — 1× in this paper · explained in 6 episodes
• Structured Reasoning — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• CLIOPATRA: Extracting Private Information from LLM Insights
• Extracting alignment data in open models
• AlpaGasus: Training A Better Alpaca with Fewer Data
• Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture
• Large-scale online deanonymization with LLMs
• Position: Privacy Is Not Just Memorization!
• Unmasking the Reality of PII Masking Models: Performance Gaps and the Call for Accountability
• Gemini: A Family of Highly Capable Multimodal Models
• Magicoder: Empowering Code Generation with OSS-Instruct
• Exploring Memorization in Fine-tuned Language Models
• Identifying and Mitigating the Influence of the Prior Distribution in Large Language Models
• Eliciting the Priors of Large Language Models using Iterated In-Context Learning

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