Search

Machine learning (ML) models have been widely applied to various applications, including image classification, text generation, audio recognition, and graph data analysis. However, recent studies have shown that ML models are vulnerable to membership inference attacks (MIAs), which aim to infer whether a data record was used to train a target model or not. MIAs on ML models can directly lead to a privacy breach. For example, via identifying the fact that a clinical record that has been used to train a model associated with a certain disease, an attacker can infer that the owner of the clinical record has the disease with a high chance. In recent years, MIAs have been shown to be effective on various ML models, e.g., classification models and generative models.Meanwhile, many defense methods have been proposed to mitigate MIAs. Although MIAs on ML models form a newly emerging and rapidly growing research area, there has been no systematic survey on this topic yet. In this article, we conduct the first comprehensive survey on membership inference attacks and defenses. We provide the taxonomies for both attacks and defenses, based on their characterizations, and discuss their pros and cons. Based on the limitations and gaps identified in this survey, we point out several promising future research directions to inspire the researchers who wish to follow this area. This survey not only serves as a reference for the research community but also provides a clear description for researchers outside this research domain. [ABSTRACT FROM AUTHOR]

Recently, biometric identification has been extensively used for border control. Some face recognition systems have been designed based on Internet of Things. But the rich personal information contained in face images can cause severe privacy breach and abuse issues during the process of identification if a biometric system has compromised by insiders or external security attacks. Encrypting the query face image is the state-of-the-art solution to protect an individual’s privacy but incurs huge computational cost and poses a big challenge on time-critical identification applications. However, due to their high computational complexity, existing methods fail to handle large-scale biometric repositories where a target face is searched. In this article, we propose an efficient privacy-preserving face recognition scheme based on clustering. Concretely, our approach innovatively matches an encrypted face query against clustered faces in the repository to save computational cost while guaranteeing identification accuracy via a novel multi-matching scheme. To the best of our knowledge, our scheme is the first to reduce the computational complexity from O(M) in existing methods to approximate O( √ M), where M is the size of a face repository. Extensive experiments on real-world datasets have shown the effectiveness and efficiency of our scheme. [ABSTRACT FROM AUTHOR]

In order to increase the power rating of electric vehicles, insulated gate bipolar translator (IGBT) modules with multiple power terminals are usually adopted. The transient current sharing of the same polarity power terminals is related to the stray inductance in the branches of the bus-bar. Based on the laminated bus-bar of a three-phase inverter in the electric vehicles that consists of asymmetrical parallel branches, this paper investigates the transient current imbalance sharing caused by the asymmetrical stray inductance in the parallel branches of the bus-bar from the view of energy storing and releasing of stray inductance for the first time. Besides, the partial self-inductance and mutual-inductance model of the parallel branches is set up. Finally, a high-precision partial stray inductance measurement method is proposed, and the accuracy of the partial stray inductance model for asymmetrical parallel branches is verified by experimental tests. [ABSTRACT FROM AUTHOR]

Hepatocellular carcinoma (HCC) is considered as a disease of dysfunction of the stem cells. Studies on stem cells have demonstrated that Oct4 plays a pivotal role in embryo regulation. In order to understand the role of Oct4 in HCC and the relationship among Oct4 and wnt/β-catenin and TGF-β signal pathways, we have detected the expression of Oct4, Nanog, Sox2, STAT3 as well as the genes in wnt/β-catenin, and TGF-β families in HCC cell lines and in tumor specimens from HCC patients. The authors found that Oct4 was expressed in all of the four HCC cell lines and the tumor specimens from HCC patients. Some other genes were also expressed in them with different level including Nanog, Sox2, STAT3 and TCF3, wnt10b, β-catenin, ELF, Smad3 and Smad4. The ability of the clone formation and migration of the HepG2 decreased after Oct4 was knockdowned. Silencing of Oct4 and TCF3 in HCC cell line HepG2 revealed that there were complicated relationships among Oct4, wnt/β-catenin family and TGF-β family genes. Knockdowning Oct4 reduced the expression of TGF-β family genes ELF, Smad3, Smad4 and wnt/β-catenin family genes, wnt10b, and β-catenin but increased TCF3. In reverse, knockdowning TCF3 led to the increased expression of Oct4 and TGF-β family genes. In conclusion, the expression of Oct4 in HCC may play an important role as in stem cell. Because Oct4 improves not only the function of wnt/β-catenin, but also the TGF-β signal pathways, the significance of its expression in HCC might be more complicated than we evinced before. [ABSTRACT FROM AUTHOR]