Android malwares severely threaten system and user security in terms of privilege escalation, remote control, tariff theft, and privacy leakage. Therefore, it is of great importance and necessity to detect Android malwares. In this paper, we present a combination method for Android malware detection based on the machine learning algorithm. First, we construct the control flow graph of the application to obtain API information. Based on the API information, we innovatively constructs boolean, frequency, and time-series data sets. Based on these three data sets, three detection models for Android malware detection regarding API calling, API frequency and API sequence aspects are constructed. Ultimately, an ensemble model is constructed for conformity. We tested and compared the accuracy and stability of our detection models through a large number of experiments. The experiments were conducted on 10010 benign applications and 10683 malicious applications. The results show that our detection model achieves 98.98% detection precision and has high accuracy and stability. All of the results are consistent with the theoretical analysis in this paper.

Nowadays, machine learning models, especially neural networks, have became prevalent in many real-world applications. These models are trained based on a one-way trip from user data: as long as users contribute their data, there is no way to withdraw. To this end, machine unlearning becomes a popular research topic, which allows the model trainer to unlearn unexpected data from a trained machine learning model. In this paper, we propose the first uniform metric called forgetting rate to measure the effectiveness of a machine unlearning method. It is based on the concept of membership inference and describes the transformation rate of the eliminated data from “memorized” to “unknown” after conducting unlearning. We also propose a novel unlearning method called Forsaken . It is superior to previous work in either utility or efficiency (when achieving the same forgetting rate). We benchmark Forsaken with eight standard datasets to evaluate its performance. The experimental results show that it can achieve more than 90% forgetting rate on average and only causeless than 5% accuracy loss.

In this paper, we propose a lightweight privacy-preserving Faster R-CNN framework (SecRCNN) for object detection in medical images. Faster R-CNN is one of the most outstanding deep learning models for object detection. Using SecRCNN, healthcare centers can efficiently complete privacy-preserving computations of Faster R-CNN via the additive secret sharing technique and edge computing. To implement SecRCNN, we design a series of interactive protocols to perform the three stages of Faster R-CNN, namely feature map extraction, region proposal and regression and classification. To improve the efficiency of SecRCNN, we improve the existing secure computation sub-protocols involved in SecRCNN, including division, exponentiation and logarithm. The newly proposed sub-protocols can dramatically reduce the number of messages exchanged during the iterative approximation process based on the coordinate rotation digital computer algorithm. Moreover, the effectiveness, efficiency and security of SecRCNN are demonstrated through comprehensive theoretical analysis and extensive experiments. The experimental findings show that the communication overhead in computing division, logarithm and exponentiation decreases to 36.19%, 73.82% and 43.37%, respectively.

The development of machine learning technology and visual sensors is promoting the wider applications of face recognition into our daily life. However, if the face features in the servers are abused by the adversary, our privacy and wealth can be faced with great threat. Many security experts have pointed out that, by 3D-printing technology, the adversary can utilize the leaked face feature data to masquerade others and break the E-bank accounts. Therefore, in this paper, we propose a lightweight privacy-preserving adaptive boosting (AdaBoost) classification framework for face recognition (POR) based on the additive secret sharing and edge computing. Firstly, we improve the current additive secret sharing based exponentiation and logarithm functions by expanding the effective input range. Then, by utilizing the protocols, two edge servers are deployed to cooperatively complete the ensemble classification of AdaBoost for face recognition. The application of edge computing ensures the efficiency and robustness of POR. Furthermore, we prove the correctness and security of our protocols by theoretic analysis. And experiment results show that, POR can reduce about 58% computation error compared with the existing differential privacy based framework.

With the rapid development of Internet of Vehicles (IoV), vehicle-based spatial crowdsourcing (SC) applications have been proposed and widely applied to various fields. However, location privacy leakage is a serious issue in spatial crowdsourcing because workers who participate in a crowdsourcing task are required to upload their driving locations. In this paper, we propose a decentralized location privacy-preserving SC for IoV, which allows vehicle users to securely participate in SC with ensuring the task's location policy privacy and providing multi-level privacy preservation for workers' locations. Specifically, we introduce blockchain technology into SC, which can eliminate the control of vehicle user data by SC-server. We combine the additively homomorphic encryption and circle-based location verification to ensure the confidentiality of task's location policy. To achieve multi-level privacy preservation for workers' driving locations, we only reveal a grid where workers are located in. The size of the grid represents the level of privacy preservation. We leverage the order-preserving encryption and non-interactive zero-knowledge proof to prevent workers from illegally obtaining rewards by forging their driving locations. The security analysis results show that our framework can satisfy the above requirements. In addition, the experiment results demonstrate that our framework is efficient and feasible in practice.