按年被提到
20172017 · 1 次2026
AI 安全、伦理与社会影响›对抗样本与后门·arXiv:1703.01340 · cs.CR

Generative Poisoning Attack Method Against Neural Networks

Chaofei Yang, Qing Wu, Hai Li, Yiran Chen · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-03-12 · 最近 2021-07-20
2不同的人
2活跃月份
2讨论串
141被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Poisoning attack is identified as a severe security threat to machine learning algorithms. In many applications, for example, deep neural network (DNN) models collect public data as the inputs to perform re-training, where the input data can be poisoned. Although poisoning attack against support vector machines (SVM) has been extensively studied before, there is still very limited knowledge about how such attack can be implemented on neural networks (NN), especially DNNs. In this work, we first examine the possibility of applying traditional gradient-based method (named as the direct gradient method) to generate poisoned data against NNs by leveraging the gradient of the target model w.r.t. the normal data. We then propose a generative method to accelerate the generation rate of the poisoned data: an auto-encoder (generator) used to generate poisoned data is updated by a reward function of the loss, and the target NN model (discriminator) receives the poisoned data to calculate the loss w.r.t. the normal data. Our experiment results show that the generative method can speed up the poisoned data generation rate by up to 239.38x compared with the direct gradient method, with slightly lower model accuracy degradation. A countermeasure is also designed to detect such poisoning attack methods by checking the loss of the target model.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论kiwih · 2021-07

“There is a name for this in machine learning, it's called a 'poisoning attack'. Essentially you add false data into a training set. An example: https://arxiv.org/abs/1703.01340”

EvilModel: Hiding Malware Inside of Neural Network Models [pdf]原评论 ↗
被提交为 story · 1 次