Invisible Optical Adversarial Stripes on Traffic Sign against Autonomous Vehicles
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917717863301120 |
|---|---|
| author | Guo, Dongfang Wu, Yuting Dai, Yimin Zhou, Pengfei Lou, Xin Tan, Rui |
| author_facet | Guo, Dongfang Wu, Yuting Dai, Yimin Zhou, Pengfei Lou, Xin Tan, Rui |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_07510 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Invisible Optical Adversarial Stripes on Traffic Sign against Autonomous Vehicles Guo, Dongfang Wu, Yuting Dai, Yimin Zhou, Pengfei Lou, Xin Tan, Rui Cryptography and Security Computer Vision and Pattern Recognition Systems and Control 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. |
| title | Invisible Optical Adversarial Stripes on Traffic Sign against Autonomous Vehicles |
| topic | Cryptography and Security Computer Vision and Pattern Recognition Systems and Control |
| url | https://arxiv.org/abs/2407.07510 |