Invariant-based online software anomaly detection and selective regression testing
Yizhen Chen · 2020
Software has been extensively used in various domains to provide online services. With the growing popularity of these types of applications, the quality of the software has a great impact on many of our daily activities [1]. Reliable software executions that deliver expected outcomes are essential for quality services. Software is considered abnormal when its behavior deviates from what is expected at any point during its execution. When anomalous behavior propagates to an exit point of the software and produces an incorrect output or an unexpected termination of the execution, it is considered a software failure. An anomaly may or may not induce a failure, but when a failure occurs there must be at least one point in the program execution that is abnormal. Software anomalous behaviors can be caused by residual code defects or anomalies propagated from the execution context.