Gargi Mitra
YOU?
Author Swipe
View article: Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices
Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices Open
The integration of AI/ML into medical devices is rapidly transforming healthcare by enhancing diagnostic and treatment facilities. However, this advancement also introduces serious cybersecurity risks due to the use of complex and often op…
View article: Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs
Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs Open
Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks (DNN) to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to…
View article: Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems
Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems Open
The adoption of machine-learning-enabled systems in the healthcare domain is on the rise. While the use of ML in healthcare has several benefits, it also expands the threat surface of medical systems. We show that the use of ML in medical …
View article: ICS-Sniper: A Targeted Blackhole Attack on Encrypted ICS Traffic
ICS-Sniper: A Targeted Blackhole Attack on Encrypted ICS Traffic Open
Operational Technology (OT) networks of industrial control systems (ICS) are increasingly connected to the public Internet, which has prompted ICSes to implement strong security measures (e.g., authentication and encryption) to protect end…
View article: White Mirror: Leaking Sensitive Information from Interactive Netflix Movies using Encrypted Traffic Analysis
White Mirror: Leaking Sensitive Information from Interactive Netflix Movies using Encrypted Traffic Analysis Open
Privacy leaks from Netflix videos/movies is well researched. Current state-of-the-art works have been able to obtain coarse-grained information such as the genre and the title of videos by passive observation of encrypted traffic. However,…