Search

Adversarial attacks can mislead deep learning models to make false predictions by implanting small perturbations to the original input that are imperceptible to the human eye, which poses a huge security threat to the computer vision systems based on deep learning. Physical adversarial attacks, which is more realistic, as the perturbation is introduced to the input before it is being captured and converted to a binary image inside the vision system, when compared to digital adversarial attacks. In this paper, we focus on physical adversarial attacks and further classify them into invasive and non-invasive. Optical-based physical adversarial attack techniques (e.g. using light irradiation) belong to the non-invasive category. As the perturbations can be easily ignored by humans as the perturbations are very similar to the effects generated by a natural environment in the real world. They are highly invisibility and executable and can pose a significant or even lethal threats to real systems. This paper focuses on optical-based physical adversarial attack techniques for computer vision systems, with emphasis on the introduction and discussion of optical-based physical adversarial attack techniques., Comment: This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible

Non-independent and identically distributed (non-IID) data is a key challenge in federated learning (FL), which usually hampers the optimization convergence and the performance of FL. Existing data augmentation methods based on federated generative models or raw data sharing strategies for solving the non-IID problem still suffer from low performance, privacy protection concerns, and high communication overhead in decentralized tabular data. To tackle these challenges, we propose a federated tabular data augmentation method, named Fed-TDA. The core idea of Fed-TDA is to synthesize tabular data for data augmentation using some simple statistics (e.g., distributions of each column and global covariance). Specifically, we propose the multimodal distribution transformation and inverse cumulative distribution mapping respectively synthesize continuous and discrete columns in tabular data from a noise according to the pre-learned statistics. Furthermore, we theoretically analyze that our Fed-TDA not only preserves data privacy but also maintains the distribution of the original data and the correlation between columns. Through extensive experiments on five real-world tabular datasets, we demonstrate the superiority of Fed-TDA over the state-of-the-art in test performance and communication efficiency.

Cloud computing is broadly recognized as one of major factors in achieving more flexible, scalable, and efficient systems. However, as customers lose the direct control of their data and applications hosted by cloud providers, the trustworthiness of cloud services is a main issue that hinders the deployment of cloud applications. In this paper, we have developed a novel framework to detect compromises on physical servers in cloud services, via remote attestation with a Trusted Third Party (TTP). Furthermore, to avoid the TTP becoming a bottleneck, we have designed a cloud based TTP platform, using a small private cloud to audit large clouds. We have implemented a prototype system, and evaluated it with several common benchmarks to demonstrate its efficiency. Our experimental results show that the proposed framework is effective in detecting compromise and adds little overhead to a common IaaS cloud environment.

Content-Addressable Storage (CAS) is a model of storage facility used for keeping immutable digital content records with peculiar advantages. This paper presents a prototype of CAS Area Network system compliant to the OSD (Object-based Storage Device) T-10 standard. The experimental results demonstrate the performance of the model is comparable to and better than that of regular storage systems. The directions about bottleneck and optimization of the real system accord with the conclusions deduced by our performance evaluation model.

For the development of artificial intelligence, several new related theories have been formulated to describe fuzzy things, such as fuzzy set, rough set, extension set, vague set and set pair analysis. This paper provides a description of the concept of all set, and analyses the relationships of fuzzy set, rough set, extension set, vague set and set pair analysis.