Mobility Profiling for User Verification with Anonymized Location Data

Authors: Miao Lin, Hong Cao, Vincent Zheng, Kevin Chen-Chuan Chang, Shonali Krishnaswamy

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimentally, our method achieves 72% verification accuracy with less than a day s data and a detection rate of 94% of illegitimate users with only 2 hours of selected data.
Researcher Affiliation Collaboration Miao Lin1, Hong Cao2, Vincent Zheng3, Kevin Chen-Chuan Chang3, Shonali Krishnaswamy1 1Institute for Infocomm Research, A*STAR, Singapore 2Mc Laren Applied Technologies, APAC 3Advanced Digital Sciences Center, UIUC, Singapore
Pseudocode Yes Algorithm 1 User verification algorithm.
Open Source Code No The paper does not provide a statement or link indicating that the source code for the methodology described is open-source or publicly available.
Open Datasets Yes We use the mobility data recorded by the Device Analyzer app [Wagner et al., 2014; 2013].
Dataset Splits Yes In the training phase, we use each user s first 9 weeks data to train the HMM, and the number of states is tested from 3 to 6. In the validation phase, we set the number of similar models and dissimilar models as the default value 5. The verification process is conducted on each user s remaining 2 to 4 weeks data.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., programming languages, libraries, or frameworks).
Experiment Setup Yes In the training phase, we use each user s first 9 weeks data to train the HMM, and the number of states is tested from 3 to 6. In the validation phase, we set the number of similar models and dissimilar models as the default value 5.