Multi-Model Running Latency Optimization in an Edge Computing Paradigm.

Recent advances in both lightweight deep learning algorithms and edge computing increasingly enable multiple model inference tasks to be conducted concurrently on resource-constrained edge devices, allowing us to achieve one goal collaboratively rather than getting high quality in each standalone task. However, the high overall running latency for performing multi-model inferences always negatively affects the real-time applications. To combat latency, the algorithms should be optimized to minimize the latency for multi-model deployment without compromising the safety-critical situation. This work focuses on the real-time task scheduling strategy for multi-model deployment and investigating the model inference using an open neural network exchange (ONNX) runtime engine. Then, an application deployment strategy is proposed based on the container technology and inference tasks are scheduled to different containers based on the scheduling strategies. Experimental results show that the proposed solution is able to significantly reduce the overall running latency in real-time applications.

ABCAttack: A Gradient-Free Optimization Black-Box Attack for Fooling Deep Image Classifiers.

The vulnerability of deep neural network (DNN)-based systems makes them susceptible to adversarial perturbation and may cause classification task failure. In this work, we propose an adversarial attack model using the Artificial Bee Colony (ABC) algorithm to generate adversarial samples without the need for a further gradient evaluation and training of the substitute model, which can further improve the chance of task failure caused by adversarial perturbation. In untargeted attacks, the proposed method obtained 100%, 98.6%, and 90.00% success rates on the MNIST, CIFAR-10 and ImageNet datasets, respectively. The experimental results show that the proposed ABCAttack can not only obtain a high attack success rate with fewer queries in the black-box setting, but also break some existing defenses to a large extent, and is not limited by model structure or size, which provides further research directions for deep learning evasion attacks and defenses.

Privacy and Security for Resource-Constrained IoT Devices and Networks: Research Challenges and Opportunities.

With the exponential growth of the Internet of Things (IoT) and cyber-physical systems (CPS), a wide range of IoT applications have been developed and deployed in recent years. To match the heterogeneous application requirements in IoT and CPS systems, many resource-constrained IoT devices are deployed, in which privacy and security have emerged as difficult challenges because the devices have not been designed to have effective security features.

Local spatial obesity analysis and estimation using online social network sensors.

Recently, the online social networks (OSNs) have received considerable attentions as a revolutionary platform to offer users massive social interaction among users that enables users to be more involved in their own healthcare. The OSNs have also promoted increasing interests in the generation of analytical, data models in health informatics. This paper aims at developing an obesity identification, analysis, and estimation model, in which each individual user is regarded as an online social network 'sensor' that can provide valuable health information. The OSN-based obesity analytic model requires each sensor node in an OSN to provide associated features, including dietary habit, physical activity, integral/incidental emotions, and self-consciousness. Based on the detailed measurements on the correlation of obesity and proposed features, the OSN obesity analytic model is able to estimate the obesity rate in certain urban areas and the experimental results demonstrate a high success estimation rate. The measurements and estimation experimental findings created by the proposed obesity analytic model show that the online social networks could be used in analyzing the local spatial obesity problems effectively.

Risk Assessment for Mobile Systems Through a Multilayered Hierarchical Bayesian Network.

Mobile systems are facing a number of application vulnerabilities that can be combined together and utilized to penetrate systems with devastating impact. When assessing the overall security of a mobile system, it is important to assess the security risks posed by each mobile applications (apps), thus gaining a stronger understanding of any vulnerabilities present. This paper aims at developing a three-layer framework that assesses the potential risks which apps introduce within the Android mobile systems. A Bayesian risk graphical model is proposed to evaluate risk propagation in a layered risk architecture. By integrating static analysis, dynamic analysis, and behavior analysis in a hierarchical framework, the risks and their propagation through each layer are well modeled by the Bayesian risk graph, which can quantitatively analyze risks faced to both apps and mobile systems. The proposed hierarchical Bayesian risk graph model offers a novel way to investigate the security risks in mobile environment and enables users and administrators to evaluate the potential risks. This strategy allows to strengthen both app security as well as the security of the entire system.

Highlighting Relationships of a Smartphone's Social Ecosystem in Potentially Large Investigations.

Social media networks are becoming increasingly popular because they can satisfy diverse needs of individuals (both personal and professional). Modern mobile devices are empowered with increased capabilities, taking advantage of the technological progress that makes them smarter than their predecessors. Thus, a smartphone user is not only the phone owner, but also an entity that may have different facets and roles in various social media networks. We believe that these roles can be aggregated in a single social ecosystem, which can be derived by the smartphone. In this paper, we present our concept of the social ecosystem in contemporary devices and we attempt to distinguish the different communities that occur from the integration of social networking in our lives. In addition, we propose techniques to highlight major actors within the ecosystem. Moreover, we demonstrate our suggested visualization scheme, which illustrates the linking of entities that live in separate communities using data taken from the smartphone. Finally, we extend our concept to include various parallel ecosystems during potentially large investigations and we link influential entities in a vertical fashion. We particularly examine cases where data aggregation is performed by specific applications, producing volumes of textual data that can be analyzed with text mining methods. Our analysis demonstrates the risks of the rising "bring your own device" trend in enterprise environments.