Shikha Badhani

It all began with an intriguing conversation amongst friends and colleagues regarding the main theme of this issue—Minds & Machines. A thought came up during our discussion that when we think about any AI system, the first thing that comes to our mind is which algorithm is used and its other ripples, like complexity, efficiency, etc. What does this AI system do, and what does it not do? But we are rarely concerned about the intention behind the creation of that AI system. If the intention is considered as the source of any AI system, the system will mirror that intention—except for any potential side effects. At the same time, the creation of any AI system also offers a unique opportunity for self-reflection. It shows a potential path toward transcending the very limitations it exposes, given that AI can process data on a level that humans cannot. The best example of this is the famous Turing Test created by Alan Turing in the year 1950 (Turing, 1950). Most of us know what the Turing Test is and what it does. In fact, it is considered the birth of artificial intelligence.

Recent years have witnessed a noticeable growth in the development of stealthy Android-based malware which has led to a pressing need for accurate malware detection systems. In this paper, we propo...

Malware creators have been very innovative when it comes to creating versions of existing malware to evade detection by anti-malware tools. Obfuscation has been the all-time favorite weapon used in malwares to hide the malicious code from being detected by analysts. These techniques are becoming more complex and sophisticated, and this motivated us to analyze Android code graphs against obfuscation. In this paper, we provide a framework for evaluating code graphs extracted from Android apps against code obfuscation. We have broadened the criteria for evaluation by employing three state-of-the-art obfuscation tools as well as app hiding techniques dedicated to the Android platform. The experimental results show that code graphs can strongly confront single level obfuscation but are vulnerable to multi-level obfuscations. Another finding is that code graphs can detect various techniques of hiding malicious app within a benign app. We also compare the code graph extraction and evaluation methodology with Androguard. This study also serves as a detailed framework for the rigorous evaluation of graph-based features against obfuscation.