TgrApp

TgrApp: Anomaly Detection and Visualization of Large-Scale Call Graphs

Authors: Mirela T. Cazzolato^1,2, Saranya Vijayakumar¹, Xinyi Zheng¹, Namyong Park¹, Meng-Chieh Lee¹, Duen Horng Chau³, Pedro Fidalgo^4,5, Bruno Lages⁴, Agma J. M. Traina², Christos Faloutsos¹.

Affiliations: ¹ Carnegie Mellon University (CMU), ² University of São Paulo (USP), ³ Georgia Institute of Technology, ⁴ Mobileum, ⁵ ISCTE-IUL

Conference: The 37th AAAI Conference on Artificial Intelligence (AAAI), 2023 @ Washington DC, USA.

Please cite the paper as (to appear):

@inproceedings{cazzolato2023tgrapp,
  title={{TgrApp}: Anomaly Detection and Visualization of Large-Scale Call Graphs},
  author={Cazzolato, M.T. and Vijayakumar, S. and Zheng, X. and Park, N. and Lee, M-C. and Chau, D.H. and Fidalgo, P. and Lages, B. and Traina, A.J.M. and Faloutsos, C..},
  booktitle={The 37th AAAI Conference on Artificial Intelligence (AAAI)},
  year={2023},
  note={To appear}
}

Requirements

Check file requirements.txt

To create and use a virtual environment, type:

python -m venv tgrapp_venv  
source tgrapp_venv/bin/activate  
pip install -r requirements.txt  

Instructions for M1 / Arm computers

For streamlit app locally on M1:

conda create --name tgrapp python=3.8  
conda install scikit-learn==0.24.2  

Comment out the scikit learn line in the requirements file (requirements.txt)
And run:

pip install -r requirements.txt  

Running the app

Run the app with the following command on your Terminal:

make
or

streamlit run app/tgrapp.py --server.maxUploadSize 8000

• Parameter [--server.maxUploadSize 8000] is optional, and it is used to increase the size limit of input files.

Data Sample

We provide a toy sample dataset in folder data/. Check file sample_raw_data.csv

Acknowledgement

Matrix cross-associations

The code for generating matrix cross-associations is originally from this Github repository.

The work was proposed in this paper:

Deepayan Chakrabarti, S. Papadimitriou, D. Modha, C. Faloutsos.
Fully automatic cross-associations. Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data
mining. 2004. DOI:10.1145/1014052.1014064.

Anomaly detection with gen²Out

The code for Gen² is originally from this Github repository.
The work was proposed in this paper:

Lee, MC., Shekhar, S., Faloutsos, C., Hutson, TN., and Iasemidis, L., gen2Out: Detecting and Ranking Generalized Anomalies. IEEE International Conference on Big Data (Big Data), 2021.

Short demo video

TgrApp-short-demo.mp4