Crowdsensing systems collect various types of data from sensors embedded on mobile devices owned by individuals. These individuals are commonly referred to as workers that complete tasks published by crowdsensing systems. Because of the relative lack of control over worker identities, crowdsensing systems are susceptible to data poisoning attacks which interfering with data analysis results by injecting fake data conflicting with ground truth. Frameworks like TruthFinder can resolve data conflicts by evaluating the trustworthiness of the data providers. These frameworks somehow make crowdsensing systems more robust since they can limit the impact of dirty data by reducing the value of unreliable workers. However, previous work has shown that TruthFinder may also be affected by data poisoning attack when the malicious workers have access to global information. In this paper, we focus on partially observable data poisoning attacks in crowdsensing systems. We show that even if the malicious workers only have access to local information, they can find effective data poisoning attack strategies to interfere with crowd sensing systems with TruthFinder. First, we formally model the problem of partially observable data poisoning attack against crowdsensing systems. Then, we propose a data poisoning attack method based on deep reinforcement learning, which helps malicious workers jeopardize with TruthFinder while hiding themselves. Based on the method, the malicious workers can learn from their attack attempts and evolve the poisoning strategies continuously. Finally, we conduct experiments on real-life data sets to verify the effectiveness of the proposed method.

Deep neural networks (DNNs) have been widely adopted but they are vulnerable to intentionally crafted adversarial examples. Various attack methods against DNNs have been proposed, yet there still lacks theoretical explanation of adversarial examples. In this paper, we aim to understand adversarial examples from the attacking process and we assume adding perturbations to the key/sensitive regions of the image could fool image classification DNNs. We propose gradient shielding to verify the assumption which ignores insensitive information during generating adversarial examples. Specifically, we propose interactive gradient shielding (IGS) method which selects sensitive regions and then applies gradient-based attack. To remove region selection, we propose adaptive gradient shielding (AGS) method which ignores insensitive gradients automatically. We conduct extensive experiments to evaluate the performance and the results also corroborate our perspective. With this method, we won the first place in IJCAI-AAAC 2019 Non-targeted Adversarial Attack competition.

The rapid growth of Android smart phones and abundant applications (Apps), a new security solution for distributed computing and mobile communications, has prompted many enhanced vendors to use different methods to effectively protect important Android files on distributed systems / servers. However, it also brings some serious distributed security problems: for example, malicious applications use reinforcement methods to hide their high-risk code, and even hide in normal applications to avoid being detected by anti-virus engines. This makes it more difficult to filter or detect malware applications. In serious cases, it will greatly affect the efficiency of mobile communication and threaten the security of distributed computers. In this paper, we propose a generic and easy to deploy and extend unpacking framework called DeepAutoD (hereinafter referred to as d-ad). By eliminating the influence of reinforcement, the framework outputs the original DEX files containing malicious features, which can provide complete feature information input for distributed machine learning based on malicious code detection. The unpacking technology solution we use integrates the deep deception call chain, which can detect the mainstream applications in the application market in a short time (a large number of malicious code will be hidden in the conventional applications), and the algorithm can adapt to any high version of Android system. Data analysis and experimental results show that the program is superior to the existing main programs in terms of safety and effectiveness.

The development of Internet of Things (IoT) dramatically facilitates the integration of computing systems with the physical world. However, as IoT devices are more easily to compromise than desktop computers, cybercriminals have founded IoT-based botnets to launch DDoS attacks with unprecedented traffic volume. To mitigate the damages associated with these attacks, the detection of IoT-based botnet has to preempt the C&C (Command and Control) communication to prevent the delivery of the attack codes.

As a networked cyber physical system, smart grid plays an important role in improving energy efficiency, which has higher prediction accuracy requirement for load forecasting to realize intelligent dispatching. The existing works of load forecasting have considered the external factors to improve prediction accuracy, but ignored their varying and different impacts in different time. In order to solve this problem, firstly, a new method is designed to select external meteorological factors and construct new features to deal with the different impacts of external factors in different seasons. Secondly, a fuzzy processing method of calendar factor is proposed to explore the varying impact of the calendar factor in the holiday period. Finally, our proposed method is combined with LSTM and other three typical machine learning models, and experiments are performed on a load data set from the real power system. The results show that our proposed method can improve the prediction accuracy of the typical machine learning based models. Especially for LSTM, the MAPEs reach to 3.8% and 3.1% in winter and summer, with the improvements of 0.6% and 0.3% respectively.