On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving

Rossolini, Giulio; Nesti, Federico; D’Amico, Gianluca; Nair, Saasha; Biondi, Alessandro; Buttazzo, Giorgio

doi:10.48550/arxiv.2201.01850

Cited by 6 publications

(7 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently a plethora of new semantic segmentation methods [16], [17], [18], [19], [20], [21], [22], [23], [24] for visual scene understanding has emerged in the literature, eliciting impressive results. For instance, Nesti et al [19] presented a method that evaluates the robustness of semantic segmentation approaches for autonomous vehicles.…”

Section: A Background and Related Workmentioning

confidence: 99%

Vision-Based Semantic Segmentation in Scene Understanding for Autonomous Driving: Recent Achievements, Challenges, and Outlooks

Muhammad

Hussain

Ullah

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Scene understanding plays a crucial role in autonomous driving by utilizing sensory data for contextual information extraction and decision making. Beyond modeling advances, the enabler for vehicles to become aware of their surroundings is the availability of visual sensory data, which expand the vehicular perception and realizes vehicular contextual awareness in real-world environments. Research directions for scene understanding pursued by related studies include person/vehicle detection and segmentation, their transition analysis, lane change, and turns detection, among many others.

show abstract

Section: A Background and Related Workmentioning

confidence: 99%

Vision-Based Semantic Segmentation in Scene Understanding for Autonomous Driving: Recent Achievements, Challenges, and Outlooks

Muhammad

Hussain

Ullah

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…After that, they test it against a simulator. Rossolini et al [28] test the robustness of semantic segmentation models by applying adversarial colored patches on the simulation and real images. The authors present extensive experiments to validate the proposed attack and defense approaches in real-world scenarios.…”

Section: Related Workmentioning

confidence: 99%

“…Our approach differs from Rossolini et al [28] since our focus is on the object detection task. Our approach also differs from [29], [27], [30] since these related works are focused on an in-depth analysis of one type of OOD data (e.g., adversarial, novelty, and distributional shift respectively).…”

Section: Related Workmentioning

confidence: 99%

SiMOOD: Evolutionary Testing Simulation With Out-Of-Distribution Images

Ferreira

Guérin

Guiochet

et al. 2022

2022 IEEE 27th Pacific Rim International Symposium on Dependable Computing (PRDC)

View full text Add to dashboard Cite

Testing perception functions for safety-critical autonomous systems is a crucial task. The reason is that accurate ML models applied in computer vision tasks still fail in scenarios where humans perform well. Out-of-distribution (OOD) images are usually a source of such failures. For this reason, literature usually applies data augmentation techniques or runtime monitors such as OOD detectors to increase robustness. Evaluating such solutions is usually performed by analyzing metrics based on positive and negative rates over a dataset containing several perturbations. However, using such metrics on such datasets can be misleading since not all OOD data lead to failures in the perception system. Hence, testing a perception system cannot be reduced to measuring Machine Learning (ML) performances on a dataset but rely on the images captured by the system at runtime. However, the amount of time spent to generate diverse test cases during a simulation of perception components can grow quickly since it is a combinatorial optimization problem. Aiming to provide a solution for this challenging task, we present SiMOOD, an evolutionary simulation testing of safety-critical perception systems, which comes integrated into the CARLA simulator. Unlike related works that simulate scenarios that raise failures for control or specific perception problems such as adversarial and novelty, we provide an approach that finds the most relevant OOD perturbations that can lead to hazards in safety-critical perception systems. Moreover, our approach can decrease, at least 10 times, the amount of time to find a set of hazards in safety-critical scenarios such as autonomous emergency braking system simulation. Besides, code is publicly available for use.

show abstract

“…This motivates us to investigate the robustness of these approaches under malicious attacks. Previous research has demonstrated that 3D perception systems can be easily compro-mised by adversarial examples [4,30,35], posing potential safety threats. However, these works primarily focus on causing a few targeted models to crash under specific conditions.…”

Section: Introductionmentioning

confidence: 99%

On the Adversarial Robustness of Camera-based 3D Object Detection

Xie¹,

Li²,

Wang³

et al. 2023

Preprint

View full text Add to dashboard Cite

In recent years, camera-based 3D object detection has gained widespread attention for its ability to achieve high performance with low computational cost. However, the robustness of these methods to adversarial attacks has not been thoroughly examined. In this study, we conduct the first comprehensive investigation of the robustness of leading camera-based 3D object detection methods under various adversarial conditions. Our experiments reveal five interesting findings: (a) the use of accurate depth estimation effectively improves robustness; (b) depth-estimationfree approaches do not show superior robustness; (c) bird'seye-view-based representations exhibit greater robustness against localization attacks; (d) incorporating multi-frame benign inputs can effectively mitigate adversarial attacks; and (e) addressing long-tail problems can enhance robustness. We hope our work can provide guidance for the design of future camera-based object detection modules with improved adversarial robustness.

show abstract

On the Real-World Adversarial Robustness of Real-Time Semantic Segmentation Models for Autonomous Driving

Cited by 6 publications

References 41 publications

Vision-Based Semantic Segmentation in Scene Understanding for Autonomous Driving: Recent Achievements, Challenges, and Outlooks

Vision-Based Semantic Segmentation in Scene Understanding for Autonomous Driving: Recent Achievements, Challenges, and Outlooks

SiMOOD: Evolutionary Testing Simulation With Out-Of-Distribution Images

On the Adversarial Robustness of Camera-based 3D Object Detection

Contact Info

Product

Resources

About