1

Characterizing Improper Input Validation Vulnerabilities of Mobile Crowdsourcing Services

(Short) Object Removal Attacks on LiDAR-based 3D Object Detectors

LiDARs play a critical role in Autonomous Vehicles’ (AVs) perception and their safe operations. Recent works have demonstrated that it is possible to spoof LiDAR return signals to elicit fake objects. In this work we demonstrate how the same physical …

Layer-wise Characterization of Latent Information Leakage in Federated Learning

Shadow-Catcher: Looking Into Shadows to Detect Ghost Objects in Autonomous Vehicle 3D Sensing

LiDAR-driven 3D sensing allows new generations of vehicles to achieve advanced levels of situation awareness. However, recent works have demonstrated that physical adversaries can spoof LiDAR return signals and deceive 3D object detectors to …

DarkneTZ: towards model privacy at the edge using trusted execution environments

We present DarkneTZ, a framework that uses an edge device's Trusted Execution Environment (TEE) in conjunction with model partitioning to limit the attack surface against Deep Neural Networks (DNNs). Increasingly, edge devices (smartphones and …

BEEER: distributed record and replay for medical devices in hospital operating rooms

Medical devices in hospital operating rooms are getting increasingly interconnected. This enables them to download instructions and report results with less risk of error compared to traditional manual techniques. However, many of these devices are …

CoDrive: Improving Automobile Positioning via Collaborative Driving

An increasing number of depth sensors and surrounding-aware cameras are being installed in the new generation of cars. For example, Tesla Motors uses a forward radar, a front-facing camera, and multiple ultrasonic sensors to enable its Autopilot …

Resolving the Predicament of Android Custom Permissions

Android leverages a set of system permissions to protect platform resources. At the same time, it allows untrusted third-party applications to declare their own custom permissions to regulate access to app components. However, Android treats custom …

Toward an Extensible Framework for Redaction

Data is being created at an increasing rate by sources like the IoT devices, social media, and camera monitors. This data frequently includes sensitive information that parties must redact to adhere to laws and user privacy policies. At the same …

CamForensics: Understanding Visual Privacy Leaks in the Wild

Many mobile apps, including augmented-reality games, bar-code readers, and document scanners, digitize information from the physical world by applying computer-vision algorithms to live camera data. However, because camera permissions for existing …