A user type identification method and system based on fine-grained cache probing
By constructing cache fingerprints through fine-grained probe resolver cache and utilizing machine learning algorithms, the problem of user type identification in encrypted DNS environments is solved, achieving low-cost and highly universal user type identification.
CN116471035BActive Publication Date: 2026-05-26INSTITUTE OF INFORMATION ENGINEERING CHINESE ACADEMY OF SCIENCES
View PDF 2 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- INSTITUTE OF INFORMATION ENGINEERING CHINESE ACADEMY OF SCIENCES
- Filing Date
- 2023-02-14
- Publication Date
- 2026-05-26
Smart Images
Figure CN116471035B_ABST
Abstract
The present invention discloses a user type recognition method and system based on fine-grained cache detection. The method is as follows: 1) Obtain the resolver address or access path within the target network range; 2) Detect the cache mode and cache structure of each resolver according to the resolver address or access path; 3) Detect the cache situation of each domain name resource record in the domain name list of each resolver in the corresponding resolver cache according to the domain name classification list and the cache structure of each resolver; Convert the cache hit situation of the domain name resource record in the resolver into a feature vector to generate the fingerprint of the corresponding resolver; 4) Use the fingerprints of each resolver as the features of the corresponding resolver, and use the known cache domain name categories of each resolver as the type labels of the corresponding resolver to construct a training data set to train the user classification model; 5) For a resolver to be recognized, input its fingerprint into the trained user classification model to obtain the user type served by the resolver to be recognized.
Need to check novelty before this filing date? Find Prior Art