Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLA
Autonomous vehicles (AVs) rely on a heterogeneous sensor suite of RGB cameras, LiDAR, GPS/IMU, and emerging event-based dynamic vision sensors (DVS) to perceive and navigate complex environments. However, these sensors can be deceived by realistic cyberattacks, undermining safety. In this work, we s...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/13/7493 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839632296677736448 |
|---|---|
| author | Mustafa Sakhai Kaung Sithu Min Khant Soe Oke Maciej Wielgosz |
| author_facet | Mustafa Sakhai Kaung Sithu Min Khant Soe Oke Maciej Wielgosz |
| author_sort | Mustafa Sakhai |
| collection | DOAJ |
| description | Autonomous vehicles (AVs) rely on a heterogeneous sensor suite of RGB cameras, LiDAR, GPS/IMU, and emerging event-based dynamic vision sensors (DVS) to perceive and navigate complex environments. However, these sensors can be deceived by realistic cyberattacks, undermining safety. In this work, we systematically implement seven attack vectors in the CARLA simulator—salt and pepper noise, event flooding, depth map tampering, LiDAR phantom injection, GPS spoofing, denial of service, and steering bias control—and measure their impact on a state-of-the-art end-to-end driving agent. We then equip each sensor with tailored defenses (e.g., adaptive median filtering for RGB and spatial clustering for DVS) and integrate a unsupervised anomaly detector (EfficientAD from anomalib) trained exclusively on benign data. Our detector achieves clear separation between normal and attacked conditions (mean RGB anomaly scores of 0.00 vs. 0.38; DVS: 0.61 vs. 0.76), yielding over 95% detection accuracy with fewer than 5% false positives. Defense evaluations reveal that GPS spoofing is fully mitigated, whereas RGB- and depth-based attacks still induce 30–45% trajectory drift despite filtering. Notably, our research-focused evaluation of DVS sensors suggests potential intrinsic resilience advantages in high-dynamic-range scenarios, though their asynchronous output necessitates carefully tuned thresholds. These findings underscore the critical role of multi-modal anomaly detection and demonstrate that DVS sensors exhibit greater intrinsic resilience in high-dynamic-range scenarios, suggesting their potential to enhance AV cybersecurity when integrated with conventional sensors. |
| format | Article |
| id | doaj-art-a2b25cc5ca3d49aab8d9f5a264cad210 |
| institution | Matheson Library |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-a2b25cc5ca3d49aab8d9f5a264cad2102025-07-11T14:36:47ZengMDPI AGApplied Sciences2076-34172025-07-011513749310.3390/app15137493Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLAMustafa Sakhai0Kaung Sithu1Min Khant Soe Oke2Maciej Wielgosz3Faculty of Computer Science, Electronics and Telecommunications, AGH University of Krakow, 30-059 Krakow, PolandFaculty of Computer Science, Electronics and Telecommunications, AGH University of Krakow, 30-059 Krakow, PolandFaculty of Computer Science, Electronics and Telecommunications, AGH University of Krakow, 30-059 Krakow, PolandFaculty of Computer Science, Electronics and Telecommunications, AGH University of Krakow, 30-059 Krakow, PolandAutonomous vehicles (AVs) rely on a heterogeneous sensor suite of RGB cameras, LiDAR, GPS/IMU, and emerging event-based dynamic vision sensors (DVS) to perceive and navigate complex environments. However, these sensors can be deceived by realistic cyberattacks, undermining safety. In this work, we systematically implement seven attack vectors in the CARLA simulator—salt and pepper noise, event flooding, depth map tampering, LiDAR phantom injection, GPS spoofing, denial of service, and steering bias control—and measure their impact on a state-of-the-art end-to-end driving agent. We then equip each sensor with tailored defenses (e.g., adaptive median filtering for RGB and spatial clustering for DVS) and integrate a unsupervised anomaly detector (EfficientAD from anomalib) trained exclusively on benign data. Our detector achieves clear separation between normal and attacked conditions (mean RGB anomaly scores of 0.00 vs. 0.38; DVS: 0.61 vs. 0.76), yielding over 95% detection accuracy with fewer than 5% false positives. Defense evaluations reveal that GPS spoofing is fully mitigated, whereas RGB- and depth-based attacks still induce 30–45% trajectory drift despite filtering. Notably, our research-focused evaluation of DVS sensors suggests potential intrinsic resilience advantages in high-dynamic-range scenarios, though their asynchronous output necessitates carefully tuned thresholds. These findings underscore the critical role of multi-modal anomaly detection and demonstrate that DVS sensors exhibit greater intrinsic resilience in high-dynamic-range scenarios, suggesting their potential to enhance AV cybersecurity when integrated with conventional sensors.https://www.mdpi.com/2076-3417/15/13/7493autonomous vehiclescybersecurity attacksdynamic vision sensor |
| spellingShingle | Mustafa Sakhai Kaung Sithu Min Khant Soe Oke Maciej Wielgosz Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLA Applied Sciences autonomous vehicles cybersecurity attacks dynamic vision sensor |
| title | Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLA |
| title_full | Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLA |
| title_fullStr | Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLA |
| title_full_unstemmed | Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLA |
| title_short | Cyberattack Resilience of Autonomous Vehicle Sensor Systems: Evaluating RGB vs. Dynamic Vision Sensors in CARLA |
| title_sort | cyberattack resilience of autonomous vehicle sensor systems evaluating rgb vs dynamic vision sensors in carla |
| topic | autonomous vehicles cybersecurity attacks dynamic vision sensor |
| url | https://www.mdpi.com/2076-3417/15/13/7493 |
| work_keys_str_mv | AT mustafasakhai cyberattackresilienceofautonomousvehiclesensorsystemsevaluatingrgbvsdynamicvisionsensorsincarla AT kaungsithu cyberattackresilienceofautonomousvehiclesensorsystemsevaluatingrgbvsdynamicvisionsensorsincarla AT minkhantsoeoke cyberattackresilienceofautonomousvehiclesensorsystemsevaluatingrgbvsdynamicvisionsensorsincarla AT maciejwielgosz cyberattackresilienceofautonomousvehiclesensorsystemsevaluatingrgbvsdynamicvisionsensorsincarla |