PrivUn: 揭示隐私去学习中的潜在涟漪效应和浅层遗忘
PrivUn: Unveiling Latent Ripple Effects and Shallow Forgetting in Privacy Unlearning
AI总结：
本文提出PrivUn框架，通过三级攻击场景和定量分析揭示隐私去学习方法的不足，发现梯度驱动的涟漪效应和浅层遗忘问题，并提出关联感知核心集选择和多层深度干预策略。
摘要：
大型语言模型（LLMs）在训练过程中常记忆私有信息，引发严重隐私问题。尽管机器去学习已成潜在解决方案，其对抗隐私攻击的有效性仍存疑。为此，我们提出PrivUn，一种新的评估框架，通过三级攻击场景：直接检索、上下文学习恢复和微调恢复，结合遗忘分数、关联度量和遗忘深度评估，系统评估去学习鲁棒性。研究揭示当前去学习方法的显著缺陷，发现两个关键结论：1）去学习表现出梯度驱动的涟漪效应：不同于传统遗忘遵循语义关系（如知识图谱），隐私去学习在潜在梯度关联中传播；2）大多数方法存在浅层遗忘，无法移除分布于多层模型中的私有信息。为验证这些见解，我们探索两种策略：关联感知核心集选择利用梯度相似性，以及通过表征约束的多层深度干预。这些策略标志着从浅层遗忘到深层遗忘的范式转变。
英文摘要：
Large language models (LLMs) often memorize private information during training, raising serious privacy concerns. While machine unlearning has emerged as a promising solution, its true effectiveness against privacy attacks remains unclear. To address this, we propose PrivUn, a new evaluation framework that systematically assesses unlearning robustness through three-tier attack scenarios: direct retrieval, in-context learning recovery, and fine-tuning restoration; combined with quantitative analysis using forgetting scores, association metrics, and forgetting depth assessment. Our study exposes significant weaknesses in current unlearning methods, revealing two key findings: 1) unlearning exhibits gradient-driven ripple effects: unlike traditional forgetting which follows semantic relations (e.g., knowledge graphs), privacy unlearning propagates across latent gradient-based associations; and 2) most methods suffer from shallow forgetting, failing to remove private information distributed across multiple deep model layers. To validate these insights, we explore two strategies: association-aware core-set selection that leverages gradient similarity, and multi-layer deep intervention through representational constraints. These strategies represent a paradigm shift from shallow forgetting to deep forgetting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
