The role of malware classification is crucial in addressing the explosive increase in malware variants. By classifying malware instances into malware families, malware analysts can apply appropriate techniques and tools to handle malware variants in each family. Using high-level representations of malware, such as disassembled codes, yields meaningful classification performance. However, malware classification based on disassembled codes depends on the practically implausible assumption that every malware is correctly reversed by disassemblers. Unfortunately, sophisticated malware, which has anti-disassembly capabilities, seeks to confuse disassemblers, yielding incorrectly disassembled codes. In this study, we focus on malware family classification, which requires no disassembly, and propose a new CNN-based malware classification model using non-disassembled malware files (i.e., binary files). Our model associates two modalities: “malware images” and “structural entropies,” which are converted and extracted from binary files. Both modalities have different granularities of bytes and chunks that complement each other. The model adopts a cross-modal attention mechanism to combine the features of the two modalities by moderating their expressive limitations. We validate our model using three popular datasets from the Kaggle Microsoft Malware Classification, Malimg, and BODMAS datasets. The experimental results show that our model identifies malware families with a higher degree of accuracy than previous methods and does not require the burden of disassembling.
31 March 2022 in Journal of Computer Science and Technology
In pervasive systems, exceptions are likely occurrences, and not rare events as is usually the case in less dynamic and more predictable systems. The uncertainty and dynamism surrounding pervasive systems require new and sophisticated approaches to defining, detecting and handling complex exceptions. In this paper, we propose exception definition strategies based on "situations" - a new and extended notion of context. Our approach enables programmers to express situation-based temporal properties of exceptions effectively, which significantly improves the overall safety of the pervasive system. In this paper, we present the notion of situation and present a programming interface for the definition of situation-based exceptions. We then present two implementation algorithms and analyze and evaluate their performance and effectiveness.
In this paper, we propose OBFUS, a web-based tool that can easily apply obfuscation techniques to high-level and low-level programming languages. OBFUS's high-level obfuscator parses and obfuscates the source code, overlaying the obfuscation to produce more complex results. OBFUS's low-level obfuscator decompiles binary programs into LLVM IR. This LLVM IR pro-gram is obfuscated and the LLVM IR program is recompiled to become an obfuscated binary program.
This paper introduces a static binary analysis tool called CrashFilter, which classifies the crashes arisen during the test, according to the risk levels. It has advantages in accuracy and provides wider coverage of analysis, due to newly introduced analyses-Memory Location Analysis and Inter-Procedure Analysis.