Vafa's research focused on leveraging machine learning for end-user security and privacy protection. This was achieved by strengthening the security and privacy defenses over the network stack: in application layer I worked on applying machine learning to build a human-centered anti-fingerprinting defense. In mid-layers I work on the MUD standard for protecting IoT devices through network-microsegmentation., and close to physical layer, I worked on deep learning applications in binary analysis for facilitating reverse engineering of stripped IoT firmware binaries.


  • MUD
  • BrowserFingerprintingCountermeasures
  • FacilitatingReverseEngineeringoftheIoTfirmware

Recent Publications

  • Vafa Andalibi, Jayati Dev, DongInn Kim, Eliot Lear, and L Jean Camp. Is Visualization Enough? Evaluating the Efficacy of MUD-Visualizer in Enabling Ease of Deployment for Manufacturer Usage Description (MUD). In Annual Computer Security Applications Conference, pages 337--348, December 2021.
    Keywords: IoT, MUD, MUD-Visualizer. [bibtex-entry]

  • Vafa Andalibi, Jayati Dev, DongInn Kim, Eliot Lear, and Jean Camp. Making Access Control Easy in IoT. In IFIP International Symposium on Human Aspects of Information Security & Assurance, June 2021.
    Keywords: IoT, MUD, MUD-Visualizer. [bibtex-entry]

  • Vafa Andalibi, Eliot Lear, DongInn Kim, and Jean Camp. On the Analysis of MUD-Files' Interactions, Conflicts, and Configuration Requirements Before Deployment. In 5th EAI International Conference on Safety and Security in Internet of Things, SaSeIoT, May 2021. Springer.
    Keywords: IoT, MUD, MUD-Visualizer. [bibtex-entry]

  • Personal Website / CV

    Want to know more about Vafa Andalibi