With the rapid growth of Android devices and applications, the Android environment faces more security threats. Malicious applications stealing usersʼ privacy information, sending text messages to trigger deductions, exploiting privilege escalation to control the system, etc., cause significant harm to end users. To detect Android malware, researchers have proposed various techniques, among which the machine learning-based methods with static features of apps as input vectors have apparent advantages in code coverage, operational efficiency, and massive sample detection. In this paper, we investigated Android applicationsʼ structure, analysed various sources of static features, reviewed the machine learning methods for detecting Android malware, studied the advantages and limitations of these methods, and discussed the future directions in this field. Our work will help researchers better understand the current research state, the benefits and weaknesses of each approach, and future technology directions.

Automatic speech recognition (ASR) is popular in our daily lives (e.g., via voice assistants or voice input). Once its security attributes are destroyed, it poses as a severe threat to a user’s life and ‘property safety’. Prior research has demonstrated that ASR systems are vulnerable to backdoor attacks. A model embedded with a backdoor behaves normally on clean samples yet misclassifies malicious samples that contain triggers. Existing backdoor attacks have mostly been conducted in the image domain. However, they can not be applied in the audio domain because of poor transferability. This paper proposes a dynamic backdoor attack method against ASR models, named DriNet. Significantly, we designed a dynamic trigger generation network to craft a variety of audio triggers. It is trained jointly with the discriminative model incorporated with an attack success rate on poisoned samples and accuracy on clean samples. We demonstrate that DriNet achieves an attack success rate of 86.4% when infecting only 0.5% of the training set without reducing its accuracy. DriNet can still achieve comparable attack performance to backdoor attacks using static triggers, further enjoying richer attack patterns. We further evaluated DriNet’s resistance to a current state-of-the-art defense mechanism. The anomaly index of DriNet is more than 37.4% smaller than that of BadNets method. The triggers generated by DriNet are hard reverse, keeping DriNet from the detectors.

Sarcasm is widely used in social communities and e-commerce platforms, failing to detect it in natural language processing tasks leads to false positives, e.g., opinion mining and sentiment classification. Recent works have indicated that the two linguistic characteristics, sentiment and incongruity information are beneficial to sarcasm detection. However, sarcasm datasets with sentiment labels are usually unavailable, and researchers consider little semantic information while modeling incongruity. In this paper, we propose a multi-task learning framework that incorporates sentiment clues by soft sentiment labels and integrates semantic information while modeling context incongruity. Experimental results on datasets show that the model we proposed yields better performance for the sarcasm detection task with the help of sentiment clues and incongruity information.

With the rapid growth of Android applications, there is an urgent need for powerful Android malware detection technology nowadays. Existing classification models can be summarized with the following two steps-feature extraction and classification model learning. To further enhance the representation ability of existing classification models, this paper presents an Android malicious application detection framework termed Multi-View Information Integration technology (MVIIDroid). To be specific, in our approach, we extract applications' multiple components, transform them into embedding feature vectors and train a Multiple Kernel Learning model as the classifier. To illustrate the effectiveness of our model, we evaluate MVIIDroid on two Android malware datasets of 6820 malware and 6820 benign applications. Results show that we have superior classification performances when separating malware from benign applications. Moreover, we further evaluate MVIIDroid's ability to attribute malicious applications to their actual families. The experimental results well demonstrate the effectiveness of the proposed model.

Sarcasm detection remains a challenge for numerous Natural Language Processing (NLP) tasks, such as sentiment classification or stance prediction. Existing sarcasm detection studies attempt to capture the subtle semantic incongruity patterns by using contextual information and graph information through Graph Convolutional Networks (GCN). However, direct application of dependence may inevitably introduce noisy information and inferiorly in modeling long-distance or disconnected words in the dependency tree. To better learn the sentiment inconsistencies between terms, we propose an Affection Enhanced Relational Graph Attention network (ARGAT) by jointly considering the affective information and the dependency information. Specifically, we use Relational Graph Attention Networks (RGAT) to integrate relation information guided by a trainable matrix of relation types and synchronously use GCNs to integrate affection information explicitly donated by affective adjacency matrixes. The employment of RGAT contributes to information interaction of structural relevant word pairs with a long distance. With the enhancement of affective information, the proposed model can capture complex forms of sarcastic expressions. Experimental results on six benchmark datasets show that our proposed approach outperforms state-of-the-art sarcasm detection methods. The best-improved results of accuracy and F1 are 4.19% and 4.33%, respectively.