The convolutional neural network (CNN)-based models have achieved tremendous breakthroughs in many end-to-end applications, such as image identification, text classification, and speech recognition. By replicating these successes to the field of malware detection, several CNN-based malware detectors have achieved encouraging performance without significant feature engineering effort in recent years. Unfortunately, by analyzing their robustness using gradient-based algorithms, several studies have shown that some of these malware detectors are vulnerable to the evasion attacks (also known as adversarial examples). However, the existing attack methods can only achieve quite low attack success rates. In this paper, we propose two novel white-box methods and one novel black-box method to attack a recently proposed malware detector. By incorporating the gradient-based algorithm, one of our white-box methods can achieve a success rate of over 99%. Without prior knowledge of the exact structure and internal parameters of the detector, the proposed black-box method can also achieve a success rate of over 70%. In addition, we consider adversarial training as a defensive mechanism in order to resist evasion attacks. While proving the effectiveness of adversarial training, we also analyze its security risk, that is, a large number of adversarial examples can poison the training dataset of the detector. Therefore, we propose a pre-detection mechanism to reject adversarial examples. The experiments show that this mechanism can effectively improve the safety and efficiency of malware detection.
Abstract-Vehicular Ad-hoc Network (VANETs) is the specific form of Mobile ad-hoc networking (MANETs) in which high dynamic nodes are utilized in carrying out the operations. They are mainly used in urban areas for safety traveling. Clustering algorithms are used for clustering the vehicles that are in the range of the network as VANET consists of a great amount of traffic. A clustering head node is used specified through a procedure to collect all information from the surroundings. This study introduced a new method for cluster head selection by using the K-Mean and Floyd-Warshall algorithms. The proposed technique first divided the points for vehicle groups while the Floyd-Warshall algorithm calculated all pairs of shortest distance for every vehicle within the defined cluster. A vehicle with the smallest average distance among a cluster is chosen as the cluster head. The Floyd-Warshall algorithm overall selects a centralized vehicle as a cluster head, hence its stability time will improve significantly.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.