.png){kind=icon}
返回
Towards explainable model extraction attacks
.png){kind=icon}
PRE
AI
DOI：10.1002/int.23022.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
One key factor able to boost the applications of artificial intelligence (AI) in security-sensitive domains is to leverage them responsibly, which is engaged in providing explanations for AI. To date, a plethora of explainable artificial intelligence (XAI) has been proposed to help users interpret model decisions. However, given its data-driven nature, the explanation itself is potentially susceptible to a high risk of exposing privacy. In this paper, we first show that the existing XAI is vulnerable to model extraction attacks and then present an XAI-aware dual-task model extraction attack (DTMEA). DTMEA can attack a target model with explanation services, that is, it can extract both the classification and explanation tasks of the target model. More specifically, the substitution model extracted by DTMEA is a multitask learning architecture, consisting of a sharing layer and two task-specific layers for classification and explanation. To reveal which explanation technologies are more vulnerable to expose privacy information, we conduct an empirical evaluation of four major explanation types in the benchmark data set. Experimental results show that the attack accuracy of DTMEA outperforms the predicted-only method with up to 1.25%, 1.53%, 9.25%, and 7.45% in MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100, respectively. By exposing the potential threats on explanation technologies, our research offers the insights to develop effective tools that are able to trade off security-sensitive relationships.
Keyword:
black box
explainable artificial intelligence
label-only
model extraction attack
期刊
IF:
3.7
论文数:
3.1K
被引数:
8.1K
机构
引用论文
.png){kind=icon}
分享收藏Resource Allocation in IoT Edge Computing via Concurrent Federated Reinforcement Learning基于并发联合强化学习的物联网边缘计算资源分配
PREAI
分享收藏
Cell-free Protein Synthesis in an Autoinduction System for NMR Studies of Protein–Protein Interactions用于NMR研究蛋白质-蛋白质相互作用的自动诱导系统中的无细胞蛋白质合成
PREAI
分享收藏Assembly of ring canals in the male germ line from structural components of the contractile ring
PREAI
分享收藏
查看更多内容