The application discloses a context-aware dependency-guided kernel fuzzing
test case mutation method and
system, and belongs to the technical field of
software security and
operating system kernel testing. The method comprises the following steps: dynamically collecting and minimizing a high-potential
system call sequence set as a
training set; modeling the dependency relationship contained in the
training set based on a neural network
language model, and using the
language model to realize context-aware dependency-guided
mutation in the
mutation stage, so as to help selecting a
system call suitable for the current context and establishing an effective state path; alternately switching between exploration and utilization stages, dynamically scheduling mutation operations through an upper bound confidence
algorithm to balance the diversity and efficiency of the test, and avoiding falling into a
local optimum; and repeating the above steps until the fuzzing test is completed. The application can improve the quality of test cases, trigger the deep code logic of the kernel, and optimize the coverage rate and the efficiency of
vulnerability mining.