Cross-platform binary code similarity detection aims at detecting whether two or more pieces of binary code are similar or not. Existing approaches that combine control flow graphs (CFGs)-based function representation and graph convolutional network (GCN)-based similarity analysis are the best-performing ones. Due to a large amount of convolutional computation and the loss of structural information, the use of convolution networks will inevitably bring problems such as high overhead and sometimes inaccuracy. To address these issues, we propose a fast cross-platform binary code similarity detection framework that takes advantage of natural language processing (NLP) and inductive graph neural network (GNN) for basic blocks embedding and function representation respectively by simulating extracting structural features and temporal features. GNN's node-centric and small batch is a suitable training way for large CFGs, it can greatly reduce computational overhead. Various NLP basic block embedding models and GNNs are evaluated. Experimental results show that the scheme with long short term memory (LSTM) for basic blocks embedding and inductive learning-based GraphSAGE(GAE) for function representation outperforms the state-of-the-art works. In our framework, we can take only 45% overhead. Improve efficiency significantly with a small performance trade-off.
20 June 2018 in Security and Communication Networks
Although existing malicious domains detection techniques have shown great success in many real-world applications, the problem of learning from imbalanced data is rarely concerned with this day. But the actual DNS traffic is inherently imbalanced; thus how to build malicious domains detection model oriented to imbalanced data is a very important issue worthy of study. This paper proposes a novel imbalanced malicious domains detection method based on passive DNS traffic analysis, which can effectively deal with not only the between-class imbalance problem but also the within-class imbalance problem. The experiments show that this proposed method has favorable performance compared to the existing algorithms.
28 July 2023 in Journal of Information Security and Applications
The increasing popularity of Industry 4.0 has led to more and more security risks, and malware adversarial attacks emerge in an endless stream, posing great challenges to user data security and privacy protection. In this paper, we investigate the stateful detection method for artificial intelligence deep learning-based malware black-box attacks, i.e., determining the presence of adversarial attacks rather than detecting whether the input samples are malicious or not. To this end, we propose the MalDBA method for experiments on the VirusShare dataset. We find that query-based black-box attacks produce a series of highly similar historical query results (also known as intermediate samples). By comparing the similarity among these intermediate samples and the trend of prediction scores returned by the detector, we can detect the presence of adversarial samples in indexed samples and thus determine whether an adversarial attack has occurred, and then protect user data security and privacy. The experimental results show that the attack detection rate can reach 100%. Compared to similar studies, our method does not require heavy feature extraction tasks or image conversion and can be operated on complete PE files without requiring a strong hardware platform.
The most severe problem in cross-programming languages is feature extraction due to different tokens in different programming languages. To solve this problem, we propose a cross-programming-language vulnerability detection method in this paper, IRC-CLVul, based on intermediate representation and combined features. Specifically, we first converted programs in different programming languages into a unified LLVM intermediate representation (LLVM-IR) to provide a classification basis for different programming languages. Afterwards, we extracted the code sequences and control flow graphs of the samples, used the semantic model to extract the program semantic information and graph structure information, and concatenated them into semantic vectors. Finally, we used Random Forest to learn the concatenated semantic vectors and obtained the classification results. We conducted experiments on 85,811 samples from the Juliet test suite in C, C++, and Java. The results show that our method improved the accuracy by 7% compared with the two baseline algorithms, and the F1 score showed a 12% increase.