MissAuditor Dataset and Software

We address the challenge in responsible computing where an exploitable mobile app is misused by one app user (an abuser) against another user or bystander (victim). We introduce the idea of a misuse audit of apps as a way of determining if they are exploitable. We leverage app reviews to identify exploitable apps and their functionalities that enable misuse. First, we build a computational model to identify alarming reviews (which report misuse). Second, using the model, we identify exploitable apps and their functionalities. Third, we validate them through manual inspection of reviews. 

The file "Annotated Reviews.csv" contains our training set and "USE-model.sav" is the computational model trained using Universal Sentence Encoder (USE) embeddings.