<b>Enhancing Android Malware Detection: The Influence of ChatGPT on Decision-centric Task</b>

We explore the transformative impact of non-decision models, specifically ChatGPT, on the traditional decision-centric task of Android malware detection. Through a series of carefully designed experiments using publicly available datasets, this study reveals a paradigm shift. It reveals a serious lack of interpretability in decision-driven solutions, raising concerns about their reliability. In contrast, ChatGPT, as a non-decision-making model, is good at providing comprehensive analysis reports and significantly enhances interpretability. We give developers more insights through a non-decision-making perspective.<b>ChatGPT</b>You can find ChatGPT’s analysis report on [APK_Analysis].<b>Project Structure</b>APK List: It contains the SHA256 of malicious and benign samples.<b>Dataset</b>All samples we used in our experiments you can find at [kronodroid].<b>Survey Results</b>We collect responses from <b>101 participants</b> and process their data by removing <b>personal or sensitive information</b>.Data preparation includes:Converting speech to textTranslating Chinese responses to EnglishRemoving redundant modal particlesThese processes ensure that the data is <b>clean and structured</b>, allowing for <b>accurate and efficient analysis</b>.<br>