Dongfang Guo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dongfang Guo has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Rui Tan
Nanyang Technological University
6 shared publications - Yuting Wu
Nanyang technological university, Singapore, Singapore
4 shared publications - Pengfei Zhou
School of Computing and Information, University of Pittsburgh, Pittsburgh, Pennsylvania, USA
3 shared publications - Xin Lou
Singapore Institute of Technology, Singapore, Singapore
3 shared publications - Qun Song
City University of Hong Kong, Hong Kong, Hong Kong
2 shared publications - Yimin Dai
Nanyang technological university, Singapore, Singapore
2 shared publications
Latest Publications
- Open Access
- 7 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 22 (1) , 1-32
Invisible Adversarial Stripes on Traffic Sign: Threat and Defense for Autonomous Vehicles
Camera-based computer vision is essential to autonomous vehicle’s perception. This article presents an attack that uses light-emitting diodes and exploits the camera’s rolling shutter effect to create adversarial stripes in the captured images to mislead traffic sign recognition. The attack is stealthy because the stripes on the traffic sign are invisible to humans. For the attack to be threatening, the recognition results need to be stable over consecutive image frames. To achieve this, we design and implement GhostStripe , an attack system that controls the timing of the modulated light emission to adapt to camera operations and victim vehicle movements. Evaluated on real testbeds, GhostStripe can stably spoof the traffic sign recognition results for up to 94% of frames to a wrong class when the victim vehicle passes the road section. In reality, such attack effect may fool victim vehicles into life-threatening incidents. To counteract this threat, we propose GhostBuster , a software-based defense module to detect and mitigate the effects of GhostStripe. GhostBuster incorporates a perturbation detector and a sign restorer, effectively restoring the natural appearance of compromised traffic signs and significantly reducing the attack’s impact. We also discuss other countermeasures at the levels of camera sensor and autonomous driving system.
- 7 January 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Sensor Networks
- Vol. 22 (1) , 1-32
Open AccessInvisible Adversarial Stripes on Traffic Sign: Threat and Defense for Autonomous Vehicles
Camera-based computer vision is essential to autonomous vehicle’s perception. This article presents an attack that uses light-emitting diodes and exploits the camera’s rolling shutter effect to create adversarial stripes in the captured images to mislead traffic sign recognition. The attack is stealthy because the stripes on the traffic sign are invisible to humans. For the attack to be threatening, the recognition results need to be stable over consecutive image frames. To achieve this, we design and implement GhostStripe , an attack system that controls the timing of the modulated light emission to adapt to camera operations and victim vehicle movements. Evaluated on real testbeds, GhostStripe can stably spoof the traffic sign recognition results for up to 94% of frames to a wrong class when the victim vehicle passes the road section. In reality, such attack effect may fool victim vehicles into life-threatening incidents. To counteract this threat, we propose GhostBuster , a software-based defense module to detect and mitigate the effects of GhostStripe. GhostBuster incorporates a perturbation detector and a sign restorer, effectively restoring the natural appearance of compromised traffic signs and significantly reducing the attack’s impact. We also discuss other countermeasures at the levels of camera sensor and autonomous driving system.
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 431-444
Dynamic Defense for Car-Borne LiDAR Vehicle Detection
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 431-444
Open AccessDynamic Defense for Car-Borne LiDAR Vehicle Detection
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 705-710
Rolling in the Deep: Exploiting Rolling Shutter Effect Against Stereo Depth Estimation in Drones
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 705-710
Open AccessRolling in the Deep: Exploiting Rolling Shutter Effect Against Stereo Depth Estimation in Drones
- Open Access
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 649-650
Time-Resolved Designs for Narrowband Radio Localization and Vehicular Visual Sensing Compromise
- 23 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 649-650
Open AccessTime-Resolved Designs for Narrowband Radio Localization and Vehicular Visual Sensing Compromise
- Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 710-711
Demo Abstract: Parameterized Stochastic Ensemble Defense for Object Detection
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 710-711
Open AccessDemo Abstract: Parameterized Stochastic Ensemble Defense for Object Detection
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 847-848
Demo: Invisible Adversarial Stripes against Traffic Sign Recognition in Autonomous Driving
Camera-based computer vision is crucial for autonomous vehicle perception. We demonstrate GhostStripe [5], an attack system that uses light-emitting diodes and exploits the camera's rolling shutter effect to generate adversarial stripes that are invisible to humans while misleading traffic sign recognition. To maintain stable attack effectiveness, GhostStripe controls the timing of the modulated light emission, adapting to both the camera's framing operation and the movement of the victim vehicle. Evaluated on real testbeds, GhostStripe can stably spoof traffic sign recognition results for up to 97% of frames to a wrong class when the victim vehicle passes the road section.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 847-848
Open AccessDemo: Invisible Adversarial Stripes against Traffic Sign Recognition in Autonomous Driving
Camera-based computer vision is crucial for autonomous vehicle perception. We demonstrate GhostStripe [5], an attack system that uses light-emitting diodes and exploits the camera's rolling shutter effect to generate adversarial stripes that are invisible to humans while misleading traffic sign recognition. To maintain stable attack effectiveness, GhostStripe controls the timing of the modulated light emission, adapting to both the camera's framing operation and the movement of the victim vehicle. Evaluated on real testbeds, GhostStripe can stably spoof traffic sign recognition results for up to 97% of frames to a wrong class when the victim vehicle passes the road section.
- Open Access
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 534-546
Invisible Optical Adversarial Stripes on Traffic Sign against Autonomous Vehicles
Camera-based computer vision is essential to autonomous vehicle's perception. This paper presents an attack that uses light-emitting diodes and exploits the camera's rolling shutter effect to create adversarial stripes in the captured images to mislead traffic sign recognition. The attack is stealthy because the stripes on the traffic sign are invisible to human. For the attack to be threatening, the recognition results need to be stable over consecutive image frames. To achieve this, we design and implement GhostStripe, an attack system that controls the timing of the modulated light emission to adapt to camera operations and victim vehicle movements. Evaluated on real testbeds, GhostStripe can stably spoof the traffic sign recognition results for up to 94% of frames to a wrong class when the victim vehicle passes the road section. In reality, such attack effect may fool victim vehicles into life-threatening incidents. We discuss the countermeasures at the levels of camera sensor, perception model, and autonomous driving system.
- 3 June 2024
- Published by Association for Computing Machinery (ACM)
- p. 534-546
Open AccessInvisible Optical Adversarial Stripes on Traffic Sign against Autonomous Vehicles
Camera-based computer vision is essential to autonomous vehicle's perception. This paper presents an attack that uses light-emitting diodes and exploits the camera's rolling shutter effect to create adversarial stripes in the captured images to mislead traffic sign recognition. The attack is stealthy because the stripes on the traffic sign are invisible to human. For the attack to be threatening, the recognition results need to be stable over consecutive image frames. To achieve this, we design and implement GhostStripe, an attack system that controls the timing of the modulated light emission to adapt to camera operations and victim vehicle movements. Evaluated on real testbeds, GhostStripe can stably spoof the traffic sign recognition results for up to 94% of frames to a wrong class when the victim vehicle passes the road section. In reality, such attack effect may fool victim vehicles into life-threatening incidents. We discuss the countermeasures at the levels of camera sensor, perception model, and autonomous driving system.