Discovering New Shadow Patterns for Black-Box Attacks on Lane Detection of 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_ | 1866912429151092736 |
|---|---|
| author | MohajerAnsari, Pedram Salarpour, Amir de Voor, Jan Domeke, Alkim Mitra, Arkajyoti Johnson, Grace Olufowobi, Habeeb Hamad, Mohammad Pese, Mert D. |
| author_facet | MohajerAnsari, Pedram Salarpour, Amir de Voor, Jan Domeke, Alkim Mitra, Arkajyoti Johnson, Grace Olufowobi, Habeeb Hamad, Mohammad Pese, Mert D. |
| contents | We present a novel physical-world attack on autonomous vehicle (AV) lane detection systems that leverages negative shadows -- bright, lane-like patterns projected by passively redirecting sunlight through occluders. These patterns exploit intensity-based heuristics in modern lane detection (LD) algorithms, causing AVs to misclassify them as genuine lane markings. Unlike prior attacks, our method is entirely passive, power-free, and inconspicuous to human observers, enabling legal and stealthy deployment in public environments. Through simulation, physical testbed, and controlled field evaluations, we demonstrate that negative shadows can cause up to 100% off-road deviation or collision rates in specific scenarios; for example, a 20-meter shadow leads to complete off-road exits at speeds above 10 mph, while 30-meter shadows trigger consistent lane confusion and collisions. A user study confirms the attack's stealthiness, with 83.6% of participants failing to detect it during driving tasks. To mitigate this threat, we propose Luminosity Filter Pre-processing, a lightweight defense that reduces attack success by 87% through brightness normalization and selective filtering. Our findings expose a critical vulnerability in current LD systems and underscore the need for robust perception defenses against passive, real-world attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18248 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Discovering New Shadow Patterns for Black-Box Attacks on Lane Detection of Autonomous Vehicles MohajerAnsari, Pedram Salarpour, Amir de Voor, Jan Domeke, Alkim Mitra, Arkajyoti Johnson, Grace Olufowobi, Habeeb Hamad, Mohammad Pese, Mert D. Cryptography and Security We present a novel physical-world attack on autonomous vehicle (AV) lane detection systems that leverages negative shadows -- bright, lane-like patterns projected by passively redirecting sunlight through occluders. These patterns exploit intensity-based heuristics in modern lane detection (LD) algorithms, causing AVs to misclassify them as genuine lane markings. Unlike prior attacks, our method is entirely passive, power-free, and inconspicuous to human observers, enabling legal and stealthy deployment in public environments. Through simulation, physical testbed, and controlled field evaluations, we demonstrate that negative shadows can cause up to 100% off-road deviation or collision rates in specific scenarios; for example, a 20-meter shadow leads to complete off-road exits at speeds above 10 mph, while 30-meter shadows trigger consistent lane confusion and collisions. A user study confirms the attack's stealthiness, with 83.6% of participants failing to detect it during driving tasks. To mitigate this threat, we propose Luminosity Filter Pre-processing, a lightweight defense that reduces attack success by 87% through brightness normalization and selective filtering. Our findings expose a critical vulnerability in current LD systems and underscore the need for robust perception defenses against passive, real-world attacks. |
| title | Discovering New Shadow Patterns for Black-Box Attacks on Lane Detection of Autonomous Vehicles |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2409.18248 |