Ricardo Mendes

Krishna Kanth Nakka, Ahmed Frikha, Ricardo Mendes et al.

The latest and most impactful advances in large models stem from their increased size. Unfortunately, this translates into an improved memorization capacity, raising data privacy concerns. Specifically, it has been shown that models can output personal identifiable information (PII) contained in their training data. However, reported PIII extraction performance varies widely, and there is no consensus on the optimal methodology to evaluate this risk, resulting in underestimating realistic adversaries. In this work, we empirically demonstrate that it is possible to improve the extractability of PII by over ten-fold by grounding the prefix of the manually constructed extraction prompt with in-domain data. Our approach, PII-Compass, achieves phone number extraction rates of 0.92%, 3.9%, and 6.86% with 1, 128, and 2308 queries, respectively, i.e., the phone number of 1 person in 15 is extractable.

Ahmed Frikha, Muhammad Reza Ar Razi, Krishna Kanth Nakka et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing but also pose significant privacy risks by memorizing and leaking Personally Identifiable Information (PII). Existing mitigation strategies, such as differential privacy and neuron-level interventions, often degrade model utility or fail to effectively prevent leakage. To address this challenge, we introduce PrivacyScalpel, a novel privacy-preserving framework that leverages LLM interpretability techniques to identify and mitigate PII leakage while maintaining performance. PrivacyScalpel comprises three key steps: (1) Feature Probing, which identifies layers in the model that encode PII-rich representations, (2) Sparse Autoencoding, where a k-Sparse Autoencoder (k-SAE) disentangles and isolates privacy-sensitive features, and (3) Feature-Level Interventions, which employ targeted ablation and vector steering to suppress PII leakage. Our empirical evaluation on Gemma2-2b and Llama2-7b, fine-tuned on the Enron dataset, shows that PrivacyScalpel significantly reduces email leakage from 5.15\% to as low as 0.0\%, while maintaining over 99.4\% of the original model's utility. Notably, our method outperforms neuron-level interventions in privacy-utility trade-offs, demonstrating that acting on sparse, monosemantic features is more effective than manipulating polysemantic neurons. Beyond improving LLM privacy, our approach offers insights into the mechanisms underlying PII memorization, contributing to the broader field of model interpretability and secure AI deployment.