Sunpreet S. Arora
YOU?
Author Swipe
View article: Compact: Approximating Complex Activation Functions for Secure Computation
Compact: Approximating Complex Activation Functions for Secure Computation Open
Secure multi-party computation (MPC) techniques can be used to provide data privacy when users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art MPC techniques can be directly leveraged for DNN models that u…
View article: Privacy-Preserving Financial Anomaly Detection via Federated Learning & Multi-Party Computation
Privacy-Preserving Financial Anomaly Detection via Federated Learning & Multi-Party Computation Open
One of the main goals of financial institutions (FIs) today is combating fraud and financial crime. To this end, FIs use sophisticated machine-learning models trained using data collected from their customers. The output of machine learnin…
View article: Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutations
Burning the Adversarial Bridges: Robust Windows Malware Detection Against Binary-level Mutations Open
Toward robust malware detection, we explore the attack surface of existing malware detection systems. We conduct root-cause analyses of the practical binary-level black-box adversarial malware examples. Additionally, we uncover the sensiti…
View article: Compact: Approximating Complex Activation Functions for Secure Computation
Compact: Approximating Complex Activation Functions for Secure Computation Open
Secure multi-party computation (MPC) techniques can be used to provide data privacy when users query deep neural network (DNN) models hosted on a public cloud. State-of-the-art MPC techniques can be directly leveraged for DNN models that u…
View article: How Interactions Influence Users' Security Perception of Virtual Reality Authentication?
How Interactions Influence Users' Security Perception of Virtual Reality Authentication? Open
Users readily embrace the rapid advancements in virtual reality (VR) technology within various everyday contexts, such as gaming, social interactions, shopping, and commerce. In order to facilitate transactions and payments, VR systems req…
View article: Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions
Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions Open
Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the ma…
View article: Practical Speech Re-use Prevention in Voice-driven Services
Practical Speech Re-use Prevention in Voice-driven Services Open
Voice-driven services (VDS) are being used in a variety of applications ranging from smart home control to payments using digital assistants. The input to such services is often captured via an open voice channel, e.g., using a microphone,…
View article: Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions
Beating Attackers At Their Own Games: Adversarial Example Detection Using Adversarial Gradient Directions Open
Adversarial examples are input examples that are specifically crafted to deceive machine learning classifiers. State-of-the-art adversarial example detection methods characterize an input example as adversarial either by quantifying the ma…
View article: DashCam Pay: A System for In-vehicle Payments Using Face and Voice
DashCam Pay: A System for In-vehicle Payments Using Face and Voice Open
We present our ongoing work on developing a system, called DashCam Pay, that enables in-vehicle payments in a seamless and secure manner using face and voice biometrics. A plug-and-play device (dashcam) mounted in the vehicle is used to ca…
View article: Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study
Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study Open
Deep learning-based systems have been shown to be vulnerable to adversarial attacks in both digital and physical domains. While feasible, digital attacks have limited applicability in attacking deployed systems, including face recognition …
View article: Referee report. For: Biometric identification of newborns and infants by non-contact fingerprinting: lessons learned [version 1; peer review: 1 approved, 1 approved with reservations]
Referee report. For: Biometric identification of newborns and infants by non-contact fingerprinting: lessons learned [version 1; peer review: 1 approved, 1 approved with reservations] Open
View article: Referee report. For: Biometric recognition of newborns and infants by non-contact fingerprinting: lessons learned [version 2; peer review: 3 approved]
Referee report. For: Biometric recognition of newborns and infants by non-contact fingerprinting: lessons learned [version 2; peer review: 3 approved] Open
View article: Universal 3D Wearable Fingerprint Targets: Advancing Fingerprint Reader\n Evaluations
Universal 3D Wearable Fingerprint Targets: Advancing Fingerprint Reader\n Evaluations Open
We present the design and manufacturing of high fidelity universal 3D\nfingerprint targets, which can be imaged on a variety of fingerprint sensing\ntechnologies, namely capacitive, contact-optical, and contactless-optical.\nUniversal 3D f…
View article: Universal 3D Wearable Fingerprint Targets: Advancing Fingerprint Reader Evaluations
Universal 3D Wearable Fingerprint Targets: Advancing Fingerprint Reader Evaluations Open
We present the design and manufacturing of high fidelity universal 3D fingerprint targets, which can be imaged on a variety of fingerprint sensing technologies, namely capacitive, contact-optical, and contactless-optical. Universal 3D fing…
View article: Biometrics for Child Vaccination and Welfare: Persistence of Fingerprint Recognition for Infants and Toddlers
Biometrics for Child Vaccination and Welfare: Persistence of Fingerprint Recognition for Infants and Toddlers Open
With a number of emerging applications requiring biometric recognition of children (e.g., tracking child vaccination schedules, identifying missing children and preventing newborn baby swaps in hospitals), investigating the temporal stabil…
View article: Biometrics for Child Vaccination and Welfare: Persistence of Fingerprint\n Recognition for Infants and Toddlers
Biometrics for Child Vaccination and Welfare: Persistence of Fingerprint\n Recognition for Infants and Toddlers Open
With a number of emerging applications requiring biometric recognition of\nchildren (e.g., tracking child vaccination schedules, identifying missing\nchildren and preventing newborn baby swaps in hospitals), investigating the\ntemporal sta…