Privacy Parameter Variation Using RAPPOR on a Malware Dataset

摘要

Stricter data protection regulations and the poor application of privacy protection techniques have resulted in a requirement for data-driven companies to adopt new methods of analysing sensitive user data. The RAPPOR (Randomized Aggregatable Privacy-Preserving Ordinal Response) method adds parameterised noise, which must be carefully selected to maintain adequate privacy without losing analytical value. This paper applies RAPPOR privacy parameter variations against a public dataset containing a list of running Android applications data. The dataset is filtered and sampled into small (10,000); medium (100,000); and large (1,200,000) sample sizes while applying RAPPOR with ? = 10; 1.0; and 0.1 (respectively low; medium; high privacy guarantees). Also, in order to observe detailed variations within high to medium privacy guarantees (? = 0.5 to 1.0), a second experiment is conducted by progressively adjusting the value of ? over the same populations. The first experiment verifies the original RAPPOR studies using ? = 1 with a non-existent recoverability in the small sample size, and detectable signal from medium to large sample sizes as also demonstrated in the original RAPPOR paper. Further results, using high privacy guarantees, show that the large sample size, in contrast to medium, suffers 2.75 times more in terms of recoverability when increasing privacy guarantees from ? = 1.0 to 0.8. Overall, the paper demonstrates that high privacy guarantees to restrict the analysis only to the most dominating strings.