Exploring Model Dynamics for Accumulative Poisoning Discovery

June 06, 2023 ยท Entered Twilight ยท ๐Ÿ› International Conference on Machine Learning

๐Ÿ’ค TWILIGHT: Eternal Rest
Repo abandoned since publication

Repo contents: LICENSE, README.md, attack_generator.py, online_accu_train_adv_relate.py, run_at.sh, run_dsc.sh, run_st.sh, train_cifar.py, utils

Authors Jianing Zhu, Xiawei Guo, Jiangchao Yao, Chao Du, Li He, Shuo Yuan, Tongliang Liu, Liang Wang, Bo Han arXiv ID 2306.03726 Category cs.LG: Machine Learning Cross-listed cs.CR Citations 0 Venue International Conference on Machine Learning Repository https://github.com/tmlr-group/Memorization-Discrepancy โญ 1 Last Checked 1 month ago
Abstract
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.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

๐Ÿ“œ Similar Papers

In the same crypt โ€” Machine Learning