Backdoor attacks have severely threatened deep neural network (DNN) models in the past several years. In backdoor attacks, the attackers try to plant hidden backdoors into DNN models, either in the training or inference stage, to mislead the output of the model when the input contains some specified triggers without affecting the prediction of normal inputs not containing the triggers. As a rapidly developing topic, numerous works on designing various backdoor attacks and developing techniques to defend against such attacks have been proposed in recent years. However, a comprehensive and holistic overview of backdoor attacks and countermeasures is still missing. In this paper, we provide a systematic overview of the design of backdoor attacks and the defense strategies to defend against backdoor attacks, covering the latest published works. We review representative backdoor attacks and defense strategies in both the computer vision domain and other domains, discuss their pros and cons, and make comparisons among them. We outline key challenges to be addressed and potential research directions in the future.

With the popularity of Android intelligent terminals, malicious applications targeting Android platform are growing rapidly. Therefore, efficient and accurate detection of Android malicious software becomes particularly important. Dynamic API call sequences are widely used in Android malware detection because they can reflect the behaviours of applications accurately. However, the raw dynamic API call sequences are very usually too long to be directly used, and most existing works just use a truncated segment of the sequence or statistical features of the sequence to perform malware detection, which loses the execution order information of applications and consequently results in high false alarm rate. In this work, we propose a method that transforms the dynamic API call sequence into a function call graph, which retains most of the application execution order information with significantly reduced sequence size. To compensate for the missed behaviour information during the transformation, the advanced features of permission requests extracted from the application are utilized. We then propose FGL_Droid, which fusions the transformed function call graph feature and the extracted permission request feature to perform accurate malware detection. Experiments on benchmark dataset show that FGL_Droid achieves a high detection accuracy of 0.975 and a high F-score of 0.978, which are better than the existing methods.

Machine learning-based Android malware detection has consistently demonstrated superior results. However, with the continual evolution of the Android framework, the efficacy of the deployed models declines markedly. Existing solutions necessitate frequent and expensive model retraining to resist the constant evolution of malware accompanying Android framework updates. To address this, we introduce a solution called ASDroid, which generalizes specific APIs into similar API clusters to counteract evolving Android malware threats. One primary challenge lies in identifying analogous API clusters that correspond to specific APIs. Our approach involves extracting semantic information from open-source API source code to construct a heterogeneous information graph, and utilizing embedding algorithms to obtain semantic vector representations of APIs. APIs that are close in embedding distance are presumed to have similar semantics. Our dataset encompasses Android applications spanning nine years from 2011 to 2019. In comparison to existing Android malware detection model aging mitigation solutions like APIGraph, SDAC and MaMaDroid, ASDroid demonstrates greater accuracy and more effective at resisting continuously evolving malware.

The popularity of the Android platform has led to an explosion in malware. The current research on Android malware mainly focuses on malware detection or malware family classification. These studies need to extract a large number of features, which consumes a lot of manpower and material resources. Moreover, some malware use obfuscation to evade decompiler tools extracting features. To address these problems, we propose ImageDroid, a method based on the image format of Android applications that can not only detect and classify malware without prior knowledge but also detect the obfuscated malware. Furthermore, we utilize the Grad-CAM interpretable mechanism of the deep learning model to automatically label the image that play a key role in determining maliciousness in a visual way. We evaluate ImageDroid over 10,000 Android applications. Experimental results show that the accuracy of malicious detection and multifamily classification achieve 97.2% and 95.1%, respectively, and the detection accuracy of obfuscated malware achieves 94.6%.

Wireless sensing has emerged as an innovative technology that enables many smart applications such as indoor localization, activity recognition, and user tracking. However, achieving reliable and precise results in wireless sensing requires an accurate distinction between line-of-sight and non-line-of-sight transmissions. This paper introduces PEiD, a novel method that utilizes low-cost WiFi devices for transmission path identification, offering real-time measurements with high accuracy through the application of machine-learning-based classifiers. To overcome the deficiencies of commodity WiFi in bandwidth, PEiD explores the peak energy index distribution extracted from the channel impulse responses. Our approach effectively captures the inherent randomness of channel properties and significantly reduces the number of samples required for identification, thus surpassing previous methods. Additionally, to tackle the challenge of mobility, a sliding window technique is also adopted to achieve continuous monitoring of transmission path status. According to our extensive experiments, PEiD can attain a best path identification accuracy of 97.5% for line-of-sight scenarios and 94.3% for non-line-of-sight scenarios, with an average delay of under 300 ms (92% accuracy) even in dynamic environments.