DP2Unlearning:为LLMs提供一个高效和保证的学习框架
Tamim Al Mahmud1, Najeeb Jebreel1, Josep Domingo-Ferrer1
1Universitat Rovira i Virgili, Department of Computer Engineering and Mathematics, CYBERCAT-Center for Cybersecurity Research of Catalonia, Av. Països Catalans 26, 43007, Tarragona Catalonia.
大型语言模型 (LLM) 现在可以使用DP2Unlearning有效地忘记数据,这是一个提供正式保证的新框架. 这种方法确保了数据隐私和模型实用性,成本低于再培训.
科学领域:
- 人工智能的人工智能
- 机器学习 机器学习
- 数据 隐私 数据 隐私 数据
背景情况:
- 大型语言模型 (LLM) 在语言任务中表现出色,但在记住私人或受版权保护的数据方面引发了伦理问题.
- 重新训练LLM以删除特定数据是有效的,但在计算上是不可避免的.
- 现有的近似的忘记方法缺乏正式的忘记保证.
研究的目的:
- 介绍DP2Unlearning,这是一个新的框架,用于有效的LLM忘记,并提供正式的忘记保证.
- 与完全再培训相比,提供一个具有成本效益的解决方案来从LLM中删除敏感信息.
- 在保持模型性能的同时,确保对数据披露的隐私.
主要方法:
- 培训LLM在以epsilon差异隐私 (DP) 保护的文本数据上.
- 使用DP受保护的模型,以实现高效的忘记,并提供正式的隐私保证.
- 将DP2Unlearning与精确的再培训和近似的学习方法进行比较.
主要成果:
- DP2Unlearning实现的模型性能与正确的unlearning (从零开始重新培训) 后的unlearning相提并论.
- 拟议的方法提供了大约一半的再培训计算成本的脱学.
- 在保持模型实用性和有效地忘记目标数据方面,DP2Unlearning的表现优于近似的unlearning方法.
结论:
- DP2Unlearning提供了一种实用和理论上合理的方法来解决LLM的学习问题.
- 该框架平衡了数据隐私,模型实用性和计算效率.
- 这种方法为解决LLM部署中的伦理和法律挑战提供了可行的解决方案.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
08:05Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques
Published on: June 30, 2020
相关概念视频
Language Development
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...
Improving Translational Accuracy
Introduction to Learning
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Generalization, Discrimination, and Extinction
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
Observational Learning
