Cross-Lingual Transferability of Training Data Extraction Attacks to Recover Memorized PII

arXiv:2610.06093 · cs.CL, cs.AI, cs.CR · Submitted 2026-10-05 · Read on arXiv

cs.CL, cs.AI, cs.CR

Submitted: 2026-10-05

Updated: 2026-10-05

Code: https://github.com/kingoflolz/mesh-transformer-jax

Project page: https://mlco2.github.io/impact

Terminology

• Transferability — 1× in this paper · explained in 4 episodes

Sources

• Quantifying Memorization Across Neural Language Models
• Scalable Extraction of Training Data from (Production) Language Models
• A Cross-Language Investigation into Jailbreak Attacks in Large Language Models
• The Pile: An 800GB Dataset of Diverse Text for Language Modeling
• Stealing Part of a Production Language Model
• KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment
• Locating and Editing Factual Associations in GPT
• OWL: Probing Cross-Lingual Recall of Memorized Texts via World Literature
• The Llama 3 Herd of Models
• Qwen2.5 Technical Report

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering