MLsploit is the first user-friendly, cloud-based system that enables researchers and practitioners to rapidly evaluate and compare state-of-the-art adversarial attacks and defenses for machine learning (ML) models.
As recent advances in adversarial ML have revealed that many ML techniques are highly vulnerable to adversarial attacks, MLsploit meets the urgent need for practical tools that facilitate interactive security testing of ML models. MLsploit is jointly developed by researchers at Georgia Tech and Intel. Designed for extensibility, MLsploit accelerates the study and development of secure ML systems for safety-critical applications. MLsploit allows performing fast-paced experimentation with adversarial ML research that spans a diverse set of modalities, such as bypassing Android and Linux malware, or attacking and defending deep learning models for image classification.
Fast, Practical Defense for Deep Learning
@article{das2018shield, title={SHIELD: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compression}, author={Das, Nilaksh and Shanbhogue, Madhuri and Chen, Shang-Tse and Hohman, Fred and Li, Siwei and Chen, Li and Kounavis, Michael E and Chau, Duen Horng}, booktitle={Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, year={2018}, organization={ACM} } "> KDD'18
1st Targeted Physical Attack on Faster R-CNN Object Detector
@inproceedings{chen2018shapeshifter, title={ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector}, author={Chen, Shang-Tse and Cornelius, Cory and Martin, Jason and Chau, Duen Horng Polo}, booktitle={Joint European Conference on Machine Learning and Knowledge Discovery in Databases}, pages={52--68}, year={2018}, organization={Springer} } "> ECML-PKDD'18
Deep Learning Software Anomaly Detection
@article{yagemann2019barnum, title={Barnum: Detecting Document Malware via Control Flow Anomalies in Hardware Traces}, author={Yagemann, Carter and Sultana, Salmin and Chen, Li and Lee, Wenke}, booktitle={Proceedings of the 22nd Information Security Conference}, year={2019}, organization={ISC} } "> ISC'19
Android Malware Detection Bypass
@article{jung2017avpass, title={AVPASS: Leaking and Bypassing Antivirus Detection Model Automatically (to appear)}, author={Jung, Jinho and Jeon, Chanil and Wolotsky, Max and Yun, Insu and Kim, Taesoo}, journal={Black Hat USA Briefings (Black Hat USA), Las Vegas, NV}, year={2017} } "> BlackHat'17
Barnum: Detecting Document Malware via Control Flow Anomalies in Hardware Traces C. Yagemann, S. Sultana, L. Chen, W. Lee. 22nd Information Security Conference 2019, New York City, USA.
MLsploit: A Cloud-Based Framework for Adversarial Machine Learning Research N. Das, S. Li, C. Jeon, J. Jung*, S. T. Chen*, C. Yagemann*, E. Downing*, H. Park, E. Yang, L. Chen, M. E. Kounavis, R. Sahita, D. Durham, S. Buck, D. H. Chau, T. Kim, W. Lee. Black Hat Asia - Arsenal 2019, Singapore.
MLsploit: A Framework for Interactive Experimentation with Adversarial Machine Learning Research N. Das, S. Li, C. Jeon, J. Jung*, S. T. Chen*, C. Yagemann*, E. Downing*, H. Park, E. Yang, L. Chen, M. E. Kounavis, R. Sahita, D. Durham, S. Buck, D. H. Chau, T. Kim, W. Lee. KDD Workshop - Project Showcase 2019, Anchorage, AK, USA.
The Efficacy of SHIELD under Different Threat Models C. Cornelius, N. Das, S. T. Chen, L. Chen, M. E. Kounavis, D. H. Chau. KDD Workshop - Learning and Mining for Cybersecurity (LEMINCS) 2019, Anchorage, AK, USA.
To believe or not to believe: Validating explanation fidelity for dynamic malware analysis L. Chen, C. Yagemann, E. Downing. CVPR 2019, Long Beach, CA, USA.
ADAGIO: Interactive Experimentation with Adversarial Attack and Defense for Audio N. Das, M. Shanbhogue, S. T. Chen, L. Chen, M. E. Kounavis, D. H. Chau. European Conference on Machine Learning & Principles & Practice of Knowledge Discovery in Databases (ECML-PKDD) 2018, Dublin, Ireland.
Compression to the Rescue: Defending from Adversarial Attacks Across Modalities N. Das, M. Shanbhogue, S. T. Chen, F. Hohman, S. Li, L. Chen, M. E. Kounavis, D. H. Chau. KDD Workshop - Project Showcase 2018, London, England.
SHIELD: Fast, Practical Defense and Vaccination for Deep Learning Using JPEG Compression N. Das, M. Shanbhogue, S. T. Chen, F. Hohman, S. Li, L. Chen, M. E. Kounavis, D. H. Chau. ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD) 2018, London, England.
ShapeShifter: Robust Physical Adversarial Attack on Faster R-CNN Object Detector S.-T. Chen, C. Cornelius, J. Martin, D. H. Chau. Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML-PKDD) 2018, Dublin, Ireland.
AVPASS: Leaking and Bypassing Antivirus Detection Model Automatically J. Jung, C. Jeon, I. Yun, M. Wolotsky, T. Kim. Black Hat 2017, Las Vegas, CA, USA.