25 citations · 25 across the 11 of their papers we have counts for
13 papers
A Secure dToF LiDAR SoC with Dual-Domain Fingerprinting and Event-Driven AFE Circuit Achieving Sensor-Level Attack Resilience
Risa Nonaka, Ryoya Matsuno, Shota Nagai +10
Recent studies have shown that most commercial direct time-of-flight (dToF) LiDARs can be spoofed by injecting high-frequency laser pulses into the receiver, which can erase pedest…
Illusion of Depth: Revealing Hidden Stereo Vision Vulnerabilities in Depth Estimation
Sri Hrushikesh Varma Bhupathiraju, Tetsu Ishizue, Nicholas U. Costagliola +4
Stereo cameras are integrated into autonomous systems such as self-driving cars, drones, and robots to offer precise depth estimation in a cost-effective manner compared to LiDAR t…
Lights, Camera, Malfunction: When Illumination Robustness Leaves VLA Models Blind to Color
Marino Watanabe, Takami Sato, Kentaro Yoshioka
Vision-Language-Action (VLA) models have emerged as a powerful paradigm for general-purpose robot manipulation; however, their transition to real-world environments reveals vulnera…
Ghost-FWL: A Large-Scale Full-Waveform LiDAR Dataset for Ghost Detection and Removal
Kazuma Ikeda, Ryosei Hara, Rokuto Nagata +6
LiDAR has become an essential sensing modality in autonomous driving, robotics, and smart-city applications. However, ghost points (or ghosts), which are false reflections caused b…
D-SLAMSpoof: An Environment-Agnostic LiDAR Spoofing Attack using Dynamic Point Cloud Injection
Rokuto Nagata, Kenji Koide, Kazuma Ikeda +2
In this work, we introduce Dynamic SLAMSpoof (D-SLAMSpoof), a novel attack that compromises LiDAR SLAM even in feature-rich environments. The attack leverages LiDAR spoofing, which…
MirrorDrift: Actuated Mirror-Based Attacks on LiDAR SLAM
Rokuto Nagata, Kenji Koide, Kazuma Ikeda +3
LiDAR SLAM provides high-accuracy localization but is fragile to point-cloud corruption because scan matching assumes geometric consistency. Prior physical attacks on LiDAR SLAM la…
BasketLiDAR: The First LiDAR-Camera Multimodal Dataset for Professional Basketball MOT
Ryunosuke Hayashi, Kohei Torimi, Rokuto Nagata +6
Real-time 3D trajectory player tracking in sports plays a crucial role in tactical analysis, performance evaluation, and enhancing spectator experience. Traditional systems rely on…
SLAMSpoof: Practical LiDAR Spoofing Attacks on Localization Systems Guided by Scan Matching Vulnerability Analysis
Rokuto Nagata, Kenji Koide, Yuki Hayakawa +6
Accurate localization is essential for enabling modern full self-driving services. These services heavily rely on map-based traffic information to reduce uncertainties in recognizi…
OSA-HCIM: On-The-Fly Saliency-Aware Hybrid SRAM CIM with Dynamic Precision Configuration
Yung-Chin Chen, Shimpei Ando, Daichi Fujiki +2
Computing-in-Memory (CIM) has shown great potential for enhancing efficiency and performance for deep neural networks (DNNs). However, the lack of flexibility in CIM leads to an un…
LiDAR Spoofing Meets the New-Gen: Capability Improvements, Broken Assumptions, and New Attack Strategies
Takami Sato, Yuki Hayakawa, Ryo Suzuki +3
LiDAR (Light Detection And Ranging) is an indispensable sensor for precise long- and wide-range 3D sensing, which directly benefited the recent rapid deployment of autonomous drivi…
Through the Looking Glass: Diminishing Occlusions in Robot Vision Systems with Mirror Reflections
Kentaro Yoshioka, Hidenori Okuni, Tuan Thanh Ta +1
The quality of robot vision greatly affects the performance of automation systems, where occlusions stand as one of the biggest challenges. If the target is occluded from the senso…
Dataset Culling: Towards Efficient Training Of Distillation-Based Domain Specific Models
Kentaro Yoshioka, Edward Lee, Simon Wong +1
Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduc…
Training Domain Specific Models for Energy-Efficient Object Detection
Kentaro Yoshioka, Edward Lee, Mark Horowitz
We propose an end-to-end framework for training domain specific models (DSMs) to obtain both high accuracy and computational efficiency for object detection tasks. DSMs are trained…