渗透蒸馏：最少样本的模型劫持
Osmosis Distillation: Model Hijacking with the Fewest Samples
AI总结：
本文提出渗透蒸馏攻击，通过最少样本实现模型劫持，揭示迁移学习中使用合成数据集的安全威胁。
摘要：
迁移学习被设计用来利用预训练模型的知识来解决新任务，以在有限的数据和计算资源下取得成效。同时，数据集蒸馏已出现，旨在合成一个紧凑的数据集，以保留原始大规模数据集的关键信息。因此，迁移学习与数据集蒸馏的结合在评估中表现出有前途的性能。然而，在使用数据集蒸馏方法生成的合成数据集中进行迁移学习时，仍然存在不容忽视的安全威胁未被发现，其中攻击者仅需在合成数据集中注入少量毒样本即可实施模型劫持攻击。为了揭示这一威胁，我们提出了渗透蒸馏（OD）攻击，一种新的模型劫持策略，旨在使用最少的样本针对深度学习模型。在各种数据集上的全面评估显示，OD攻击在隐藏任务中实现了高攻击成功率，同时在原始任务中保持了高模型效用。此外，蒸馏的渗透集使模型劫持能够跨越多样的模型架构，允许在迁移学习中实现显著的攻击性能和模型效用。我们主张必须提高对在迁移学习中使用第三方合成数据集的意识。
英文摘要：
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation has emerged to synthesize a compact dataset that preserves critical information from the original large dataset. Therefore, a combination of transfer learning and dataset distillation offers promising performance in evaluations. However, a non-negligible security threat remains undiscovered in transfer learning using synthetic datasets generated by dataset distillation methods, where an adversary can perform a model hijacking attack with only a few poisoned samples in the synthetic dataset. To reveal this threat, we propose Osmosis Distillation (OD) attack, a novel model hijacking strategy that targets deep learning models using the fewest samples. Comprehensive evaluations on various datasets demonstrate that the OD attack attains high attack success rates in hidden tasks while preserving high model utility in original tasks. Furthermore, the distilled osmosis set enables model hijacking across diverse model architectures, allowing model hijacking in transfer learning with considerable attack performance and model utility. We argue that awareness of using third-party synthetic datasets in transfer learning must be raised.
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。
