Tokenized Key-Gated Adapter Routing: A Secure Access Control Mechanism Against Private Data Leakage in LLMs

arXiv:2610.00309 · cs.CR, cs.AI, cs.CL · Submitted 2026-09-28 · Read on arXiv

cs.CR, cs.AI, cs.CL

Submitted: 2026-09-28

Updated: 2026-09-28

Code: https://github.com/data-privacy-stack/presidio

Terminology

• Accuracy — 37× in this paper · explained in 1 episode
• Fine-Tuning — 28× in this paper · explained in 5 episodes
• Perplexity — 20× in this paper · explained in 3 episodes
• Differential Privacy — 11× in this paper · explained in 4 episodes
• AUC — 10× in this paper · explained in 2 episodes
• LoRA Adapters — 9× in this paper · explained in 3 episodes
• Adaptation — 8× in this paper · explained in 1 episode
• Embeddings — 7× in this paper · explained in 2 episodes
• Robustness — 6× in this paper · explained in 5 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Differentially Private — 3× in this paper · explained in 3 episodes
• Modularity — 3× in this paper · explained in 9 episodes
• Tokenization — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Fidelity — 2× in this paper · explained in 2 episodes
• Gradient Flow — 2× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Loss Function — 2× in this paper · explained in 2 episodes
• PROACTIVE PRIVACY AMNESIA — 2× in this paper
• Regularization — 2× in this paper · explained in 3 episodes
• Transformer — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Adversarial Prompting — 1× in this paper · explained in 1 episode
• Analyzer — 1× in this paper · explained in 1 episode
• Computational overhead — 1× in this paper · explained in 2 episodes
• Computer Security Foundations Symposium — 1× in this paper
• Core — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Differential Privacy (DP) — 1× in this paper · explained in 7 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Information Leakage — 1× in this paper · explained in 2 episodes
• LoRA (Low-Rank Adaptation) — 1× in this paper · explained in 3 episodes
• LoRA Fine-Tuning — 1× in this paper · explained in 3 episodes
• Low-Rank Adaptation (LoRA) — 1× in this paper · explained in 9 episodes
• Mixture-of-Experts (MoE) — 1× in this paper · explained in 7 episodes
• Model Merging — 1× in this paper · explained in 2 episodes
• Multimodal Learning — 1× in this paper · explained in 2 episodes
• Named Entity Recognition (NER) — 1× in this paper · explained in 2 episodes
• Parameter Efficiency — 1× in this paper · explained in 3 episodes
• Prompt Engineering — 1× in this paper · explained in 4 episodes
• Quantization — 1× in this paper · explained in 12 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Synthetic Data Generation — 1× in this paper · explained in 5 episodes
• Transformer Architecture — 1× in this paper · explained in 2 episodes

Sources

• GPT-4 Technical Report
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• PaLM 2 Technical Report
• Gemini: A Family of Highly Capable Multimodal Models
• BloombergGPT: A Large Language Model for Finance
• Scalable Extraction of Training Data from (Production) Language Models
• Lateral Phishing With Large Language Models: A Large Organization Comparative Study
• LLM-PBE: Assessing Data Privacy in Large Language Models
• PII-Scope: A Comprehensive Study on Training Data PII Extraction Attacks in LLMs
• Large Language Models Can Be Strong Differentially Private Learners
• Aligning Language Models with Preferences through f-divergence Minimization
• LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
• LoRA: Low-Rank Adaptation of Large Language Models
• Gemma: Open Models Based on Gemini Research and Technology
• The Llama 3 Herd of Models
• Qwen3 Technical Report
• Decoupled Weight Decay Regularization
• Data Extraction Attacks in Retrieval-Augmented Generation via Backdoors
• Are Medium-Sized Transformers Models still Relevant for Medical Records Processing?
• Multi-objective Representation for Numbers in Clinical Narratives: A CamemBERT-Bio-Based Alternative to Large-Scale LLMs

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