The collaborative inference approach splits the Deep Neural Networks (DNNs) model into two parts. It runs collaboratively on the end device and cloud server to minimize inference latency and protect data privacy, especially in the 5G era. The scheme of DNN model partitioning depends on the network bandwidth size. However, in the context of dynamic mobile networks, resource-constrained devices cannot efficiently execute complex model partitioning algorithms to obtain optimal partitioning in real-time. In this paper, to overcome this challenge, we first formulate the model partitioning problem as a Min-cut problem to seek the optimal partition. Second, we propose a Collaborative Inference method based on model Compression named CIC. CIC enhances the efficiency of the execution of model partitioning algorithms on resource-constrained end devices by reducing the algorithm's complexity. CIC generates a splitting model based on the inherent characteristics of the DNN model and the platform resources. The splitting models are independent of the network environment, generated offline, and constantly used in the current environment. CIC has excellent compressibility, and even DNN models with hundreds of layers can be rapidly partitioned on resource-constrained devices. Experimental results show that our method is significantly more effective than existing solutions, speeding up model partitioning decision time by up to 100x, reducing inference latency by up to 2.6x, and increasing throughput by up to 3.3x in the best case.

Recent years have witnessed lots of attacks targeted at the widespread Internet of Things (IoT) devices and malicious activities conducted by compromised IoT devices. After some notorious IoT malware released their source code, many new variants emerge, which are usually more powerful and stealthy. Although numerous existing studies have analyzed some exposed families, there is a lack of systematic study to make full use of them, which can be a fundamental step for provenance, triage, labeling, lineage analysis, and authorship attribution. The key challenge of conducting an IoT malware evolutionary study is how to collect sufficient and accurate information about malware and identify the relationships among them. In this article, we take the first step to investigate the IoT malware evolution by leveraging the information from two sources that complement each other. First, we crawl online articles about IoT malware and employ natural language processing techniques to extract the features of malware samples and their relationships with other malware family, which allow us to form the basic lineage graph. Second, we collect real malware samples through our widely deployed honeypots and design a new classifier to group them into families and identify lineage relationships among them. Such results are used to enhance the basic lineage graph. Eventually, we construct the final lineage graph for 72 IoT malware families by correlating the information from the aforementioned sources, which can help the research community better understand and fight IoT malware now and in the future. Our study has been incorporated into the threat awareness system of NSFOCUS company.

With the boom of Augmented Reality (AR) and Virtual Reality (VR) applications, head-mounted smart wearable glass devices are becoming popular to help users access various services like E-mail freely. However, most existing password entry schemes on smart glasses rely on additional computers or mobile devices connected to smart glasses, which require users to switch between different systems and devices. This may greatly lower the practicability and usability of smart glasses. In this paper, we focus on this challenge and design three practical anti-eavesdropping password entry schemes on stand-alone smart glasses, named gTapper, gRotator and gTalker. The main idea is to break the correlation between the underlying password and the interaction observable to adversaries. In our IRB-approved user study, these schemes are found to be easy-to-use without additional hardware under various test conditions, where the participants can enter their passwords within moderate time, at high accuracy, and in various situations.

Face authentication is vulnerable to media-based virtual face forgery (MVFF) where adversaries display photos/videos or 3D virtual face models of victims to spoof face authentication systems. In this paper, we propose a liveness detection mechanism, called FaceCloseup, to protect the face authentication on mobile devices. FaceCloseup detects MVFF-based attacks by analyzing the distortion of face regions in a user's closeup facial videos captured by built-in camera on mobile device. It can detect MVFF-based attacks with an accuracy of 99.48%.

Face authentication has been widely available on smartphones, tablets, and laptops. As numerous personal images are published in online social networks (OSNs), OSN-based facial disclosure (OSNFD) creates significant threat against face authentication. We make the first attempt to quantitatively measure OSNFD threat to real-world face authentication systems on smartphones, tablets, and laptops. Our results show that the percentage of vulnerable users that are subject to spoofing attacks is high, which is about 64 percent for laptop users, and 93 percent smartphone/tablet users. We investigate liveness detection methods in the real-world face authentication systems against OSNFD threat. We discover that under protection of liveness detection, the percentage of vulnerable images is 18.8 percent, but the percentage of vulnerable users is as high as 73.3 percent. This evidence suggests that the current face authentication systems are not strong enough under OSNFD attacks. Finally, we develop a risk estimation tool based on logistic regression, and analyze the impacts of key attributes of facial images on the OSNFD risk. Our statistical analysis reveals that the most influential attributes of facial images are image resolution, facial makeup, occluded eyes, and illumination. This tool can be used to evaluate OSNFD risk for OSN images to increase users' awareness of OSNFD.

Smart glasses are becoming popular for users to access various services such as email. To protect these services, password-based user authentication is widely used. Unfortunately, the password-based user authentication has inherent vulnerability against password leakage. Many efforts have been put on designing leakage-resilient password entry schemes on PCs and mobile phones with traditional input equipment including keyboards and touch screens. However, such traditional input equipment is not available on smart glasses. Existing password entry on smart glasses relies on additional PCs or mobile devices. Such solutions force users to switch between different systems, which causes interrupted experience and may lower the practicability and usability of smart glasses. In this paper, we propose a series of leakage-resilient password entry schemes on stand-alone smart glasses, which are gTapper, gRotator, and gTalker. These schemes ensure no leakage in password entry by breaking the correlation between the underlying password and the interaction observable to adversaries. They are practical in the sense that they only require a touch pad, a gyroscope, and a microphone which are commonly available on smart glasses. The usability of the proposed schemes is evaluated by user study under various test conditions which are common in users' daily usage. The results of our user study reveal that the proposed schemes are easy-to-use so that users enter their passwords within moderate time, at high accuracy, and in various situations.

Leveraging built-in cameras on smartphones and tablets, face authentication provides an attractive alternative of legacy passwords due to its memory-less authentication process. However, it has an intrinsic vulnerability against the media-based facial forgery (MFF) where adversaries use photos/videos containing victims' faces to circumvent face authentication systems. In this paper, we propose FaceLive, a practical and robust liveness detection mechanism to strengthen the face authentication on mobile devices in fighting the MFF-based attacks. FaceLive detects the MFF-based attacks by measuring the consistency between device movement data from the inertial sensors and the head pose changes from the facial video captured by built-in camera. FaceLive is practical in the sense that it does not require any additional hardware but a generic front-facing camera, an accelerometer, and a gyroscope, which are pervasively available on today's mobile devices. FaceLive is robust to complex lighting conditions, which may introduce illuminations and lead to low accuracy in detecting important facial landmarks; it is also robust to a range of cumulative errors in detecting head pose changes during face authentication.

Face authentication is one of promising biometrics-based user authentication mechanisms that have been widely available in this era of mobile computing. With built-in camera capability on smart phones, tablets, and laptops, face authentication provides an attractive alternative of legacy passwords for its memory-less authentication process. Although it has inherent vulnerability against spoofing attacks, it is generally considered sufficiently secure as an authentication factor for common access protection. However, this belief becomes questionable since image sharing has been popular in online social networks (OSNs). A huge number of personal images are shared every day and accessible to potential adversaries. This OSN-based facial disclosure (OSNFD) creates a significant threat against face authentication. In this paper, we make the first attempt to quantitatively measure the threat of OSNFD. We examine real-world face-authentication systems designed for both smartphones, tablets, and laptops. Interestingly, our results find that the percentage of vulnerable images that can used for spoofing attacks is moderate, but the percentage of vulnerable users that are subject to spoofing attacks is high. The difference between systems designed for smartphones/tablets and laptops is also significant. In our user study, the average percentage of vulnerable users is 64% for laptop-based systems, and 93% for smartphone/tablet-based systems. This evidence suggests that face authentication may not be suitable to use as an authentication factor, as its confidentiality has been significantly compromised due to OSNFD. In order to understand more detailed characteristics of OSNFD, we further develop a risk estimation tool based on logistic regression to extract key attributes affecting the success rate of spoofing attacks. The OSN users can use this tool to calculate risk scores for their shared images so as to increase their awareness of OSNFD.