arXiv:2502.15796cs.LGcs.AI2025-02被引 4
剪枝能有效减少大模型对训练数据的记忆，提升隐私安全。
Pruning as a Defense: Reducing Memorization in Large Language Models
- 通过简单剪枝降低模型对训练数据的记忆能力。
- 剪枝后模型重现训练数据的能力显著下降。
- 适合关注模型隐私保护的研究者与工程师。
大型语言模型已被证明会记忆其训练数据的大量内容，当受到适当提示时可复现这些数据。本文研究了简单剪枝技术对此行为的影响。结果表明，剪枝能有效降低大模型的记忆程度，展现出其作为缓解成员推理攻击的基础性方法的潜力。
原文摘要 · Abstract (English)
Large language models have been shown to memorize significant portions of their training data, which they can reproduce when appropriately prompted. This work investigates the impact of simple pruning techniques on this behavior. Our findings reveal that pruning effectively reduces the extent of memorization in LLMs, demonstrating its potential as a foundational approach for mitigating membership inference attacks.
模型压缩隐私保护剪枝
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。