Publications

• Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs

  Authors: Mohammed Elnawawy, Gargi Mitra, Shahrear Iqbal, Karthik Pattabiraman

  Publication Venue: Workshop on Dependable and Secure Machine Learning (DSML), 2025

  Acceptance Rate: 64 %

  Link to paper

• Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices

  Authors: Gargi Mitra, Mohammadreza Hallajiyan1, Inji Kim, Athish Pranav Dharmalingam, Mohammed Elnawawy, Shahrear Iqbal, Karthik Pattabiraman, Homa Alemzadeh

  Publication Venue: Springer Nature 2024 Journal on International Conference on Cybersecurity in Healthcare

  Link to paper

• MedAIScout: Automated Retrieval of Known Machine Learning Vulnerabilities in Medical Applications

  Authors: Gargi Mitra (UBC), Athish Pranav Dharmalingam (IIT Madras)

  Publication Venue: NeurIPS 2024 Workshop on "Red Teaming GenAI: What Can We Learn from Adversaries?"

  Link to paper

• Systematically Assessing the Security Risks ofAI/ML-enabled Connected Healthcare Systems

  Authors: Mohammed Elnawawy (UBC), Mohammadreza Hallajiyan (UBC), Gargi Mitra (UBC), Shahrear Iqbal (NRC Canada), Karthik Pattabiraman (UBC)

  Publication Venue: IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE) 2024

  Acceptance Rate: 28.4 %

  Link to paper | Link to code | Link to list of data sources used for analysis

• SAM: Foreseeing Inference-Time False Data Injection Attacks onML-enabled Medical Devices

  Authors: Mohammadreza Hallajiyan (UBC), Athish Pranav Dharmalingam (IIT Madras), Gargi Mitra (UBC), Shahrear Iqbal (NRC Canada), Karthik Pattabiraman (UBC)

  Publication Venue: HealthSec 2024, a workshop co-located with ACM CCS 2024

  Acceptance Rate: 57 %

  Link to paper