About

I am a Senior Researcher at Huawei’s Turing Research Center. My research is at the intersection of AI and computer systems, with a focus on safe and resilient AI agents. I develop techniques to protect AI agents against failures and adversarial threats, enabling reliable operation even under adversarial and unforeseen conditions.

Previously, I completed my Ph.D. in Electrical and Computer Engineering from the University of British Columbia (UBC), where I was a member of the Dependable Systems Lab advised by Prof. Karthik Pattabiraman. I received my master’s degree from UBC in 2020 and my undergrad degree from Vellore Institute of Technology, India in 2016. Before joining UBC, I worked as a Research Engineer at IAIK, Graz University of Technology. In that role I contributed to CREDENTIAL EU Horizon 2020 Project. In the past I interned at Oracle Labs (2022), Institute of Infocomm Research, A*Star in Singapore (2016), Fraunhofer SIT in Germany (2015).

Awards and Honors

  • Rising Stars Award for research in cyber-physical systems [link] 2024
  • Academic excellence award from University of British Columbia (UBC) 2020-2024
  • Exemplary talk mentions @Usenix Enigma'2022 [link] 2024
  • Four year fellowship (4YF) from University of British Columbia (UBC) 2020
  • DAAD WISE fellowship 2015

Talks

  • Detection Is Not Enough: Attack Recovery for Safe and Robust Autonomous Robotic Vehicles
    [slides] [talk]
    Usenix Enigma 2022
  • Crash, Fail-safe, or Recover: Securing Robotic Autonomous Vehicles
    [slides]
    VehicleSec 2025 at Usenix Security

Selected Publications

  • RAVAGE: Robotic Autonomous Vehicles' Attack Generation Engine
    Pritam Dash , Karthik Pattabiraman
    [DSN'25] IEEE/IFIP International Conference on Dependable Systems and Networks
    [PDF] [Code]
  • SpecGuard: Specification Aware Recovery for Robotic Autonomous Vehicles from Physical Attacks
    Pritam Dash , Ethan Chan, Karthik Pattabiraman
    [CCS'24] ACM SIGSAC Conference on Computer and Communications Security
    [PDF] [Code]
  • Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks
    Pritam Dash , Guanpeng Li, Mehdi Karimibiuki, Karthik Pattabiraman
    [AsiaCCS'24] ACM ASIA Conference on Computer and Communications Security
    [PDF] [Code]
  • Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks
    Zitao Chen, Pritam Dash , Karthik Pattabiraman
    [AsiaCCS'23] ACM ASIA Conference on Computer and Communications Security
    [PDF] [Code]
  • PID-Piper: Recovering Robotic Vehicles from Physical Attacks
    Pritam Dash , Guanpeng Li, Zitao Chen, Mehdi Karimibiuki, Karthik Pattabiraman
    [DSN'21] IEEE/IFIP International Conference on Dependable Systems and Networks
    [PDF] [Code]
    Best Paper Award