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:1712.05526 · cs.CR

Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning

Xinyun Chen, Chang Liu, Bo Li, Kimberly Lu, Dawn Song · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-12-21 · 最近 2023-02-25
2不同的人
2活跃月份
2讨论串
1,039被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many security-sensitive applications like payment apps. Such usages of deep learning systems provide the adversaries with sufficient incentives to perform attacks against these systems for their adversarial purposes. In this work, we consider a new type of attacks, called backdoor attacks, where the attacker's goal is to create a backdoor into a learning-based authentication system, so that he can easily circumvent the system by leveraging the backdoor. Specifically, the adversary aims at creating backdoor instances, so that the victim learning system will be misled to classify the backdoor instances as a target label specified by the adversary. In particular, we study backdoor poisoning attacks, which achieve backdoor attacks using poisoning strategies. Different from all existing work, our studied poisoning strategies can apply under a very weak threat model: (1) the adversary has no knowledge of the model and the training set used by the victim system; (2) the attacker is allowed to inject only a small amount of poisoning samples; (3) the backdoor key is hard to notice even by human beings to achieve stealthiness. We conduct evaluation to demonstrate that a backdoor adversary can inject only around 50 poisoning samples, while achieving an attack success rate of above 90%. We are also the first work to show that a data poisoning attack can create physically implementable backdoors without touching the training process. Our work demonstrates that backdoor poisoning attacks pose real threats to a learning system, and thus highlights the importance of further investigation and proposing defense strategies against them.

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yorwba · 2017-12

“I would have liked to read the actual paper, but the arXiv link leads to something completely unrelated: https://arxiv.org/abs/1712.05526 Does anyone have a correct link?”

Courtroom AI system claims almost 90 percent accuracy in detecting lies原评论 ↗
评论moyix · 2023-02

“Adversarial attacks are inference-time, backdoors are training time. This paper isn't the first to propose the idea of backdooring DNNs (I believe our paper [1], concurrently with a couple others [2,3], did that). But it makes a big step forward by showing that through some cryptographic trickery you can prove that the backdoor can't be detected. [1] htt…”

Planting Undetectable Backdoors in Machine Learning Models原评论 ↗