Exploring Model Dynamics for Accumulative Poisoning Discovery

Autor:	Zhu, Jianing, Guo, Xiawei, Yao, Jiangchao, Du, Chao, He, Li, Yuan, Shuo, Liu, Tongliang, Wang, Liang, Han, Bo
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Cryptography and Security
Druh dokumentu:	Working Paper
Popis:	Adversarial poisoning attacks pose huge threats to various machine learning applications. Especially, the recent accumulative poisoning attacks show that it is possible to achieve irreparable harm on models via a sequence of imperceptible attacks followed by a trigger batch. Due to the limited data-level discrepancy in real-time data streaming, current defensive methods are indiscriminate in handling the poison and clean samples. In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information. By implicitly transferring the changes in the data manipulation to that in the model outputs, Memorization Discrepancy can discover the imperceptible poison samples based on their distinct dynamics from the clean samples. We thoroughly explore its properties and propose Discrepancy-aware Sample Correction (DSC) to defend against accumulative poisoning attacks. Extensive experiments comprehensively characterized Memorization Discrepancy and verified its effectiveness. The code is publicly available at: https://github.com/tmlr-group/Memorization-Discrepancy. Comment: accepted by ICML 2023
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2306.03726 Zobrazit plný text záznamu View this record from Arxiv