MobilBye: Attacking ADAS with Camera Spoofing

Nassi, Dudi; Ben-Netanel, Raz; Elovici, Yuval; Nassi, Ben

doi:10.48550/arxiv.1906.09765

Cited by 12 publications

(13 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First, harsh weather conditions such as foggy and snowy weather could reduce the capabilities of the intelligent sensors. Besides that, physical noise or fake signal data, namely, jamming attack [13][14][15][16] and spoofing attack [13,[17][18][19] (see details in §6.1.2) may also exist in the driving environment, and could interfere these sensors and harm their normal functionalities.…”

Section: The Threat Modelmentioning

confidence: 99%

A Survey on Automated Driving System Testing: Landscapes and Trends

Tang¹,

Zhang²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automated Driving Systems (ADS) have made great achievements in recent years thanks to the efforts from both academia and industry. A typical ADS is composed of multiple modules, including sensing, perception, planning and control, which brings together the latest advances in multiple domains. Despite these achievements, safety assurance of the systems is still of great significance, since the unsafe behavior of ADS can bring catastrophic consequences and unacceptable economic and social losses. Testing is an important approach to system validation for the deployment in practice; in the context of ADS, it is extremely challenging, due to the system complexity and multidisciplinarity. There has been a great deal of literature that focuses on the testing of ADS, and a number of surveys have also emerged to summarize the technical advances. However, most of these surveys focus on the system-level testing that is performed within software simulators, and thereby ignore the distinct features of individual modules. In this paper, we provide a comprehensive survey on the existing ADS testing literature, which takes into account both module-level and system-level testing. Specifically, we make the following contributions: (1) we build a threat model that reveals the potential safety threats for each module of an ADS; (2) we survey the module-level testing techniques for ADS and highlight the technical differences affected by the properties of the modules; (3) we also survey the system-level testing techniques, but we focus on empirical studies that take a bird's-eye view on the system, the problems due to the collaborations between modules, and the gaps between ADS testing in simulators and real world; (4) we identify the challenges and opportunities in ADS testing, which facilitates the future research in this field. CCS Concepts: • Computer systems organization → Embedded systems; • Software and its engineering → Software verification and validation; • Security and privacy → Systems security; • Computing methodologies → Artificial intelligence.

show abstract

Section: The Threat Modelmentioning

confidence: 99%

A Survey on Automated Driving System Testing: Landscapes and Trends

Tang¹,

Zhang²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This capability allows the attacker to outright replace the image with one that does not correspond to the world that is being observed and trivially enables serious compromises. However, in a lot of the systems we observed, adversaries do not have that kind of access and they need to either find ways to project fake objects (as in [Nassi et al, 2019]) or be more subtle and create physical adversarial objects (as in [Sharif et al, 2016, Eykholt et al, 2018, Brown et al, 2017). The relative increase in work factor for attackers is large, even though attacks are still possible.…”

Section: Robust Input Modalitiesmentioning

confidence: 99%

“…Attackers can find out-of-distribution inputs that do not fit in with the inputs that the model designer imagined. For example, Nassi et al [2019] demonstrates an attack that fools an autonomous vehicle into stopping or veering out of its lane by simply projecting false images of stop signs, pedestrians, and lane markers onto and around a road. Sufficiently realistic projections of light onto the road are enough to cause the vehicle to violate its security guarantees.…”

Section: Adaptive Defenses For Adaptive Adversariesmentioning

confidence: 99%

Security and Machine Learning in the Real World

Evtimov

Cui

Kamar

et al. 2020

Preprint

View full text Add to dashboard Cite

Machine learning (ML) models deployed in many safety-and business-critical systems are vulnerable to exploitation through adversarial examples. A large body of academic research has thoroughly explored the causes of these blind spots, developed sophisticated algorithms for finding them, and proposed a few promising defenses. A vast majority of these works, however, study standalone neural network models. In this work, we build on our experience evaluating the security of a machine learning software product deployed on a large scale to broaden the conversation to include a systems security view of these vulnerabilities. We describe novel challenges to implementing systems security best practices in software with ML components. In addition, we propose a list of short-term mitigation suggestions that practitioners deploying machine learning modules can use to secure their systems. Finally, we outline directions for new research into machine learning attacks and defenses that can serve to advance the state of ML systems security.

show abstract

“…Recent academic work has produced many examples of disrupting camera-based intelligent systems using projections on surfaces in the environment [26], [31], [61], or the placement of printed patches [13]. Attacks inhibiting the use of camera footage are well known and repeatedly shown in different settings [35], [58].…”

Section: Introductionmentioning

confidence: 99%

They See Me Rollin’: Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensors

Köhler

Lovisotto

Birnbach

et al. 2021

Annual Computer Security Applications Conference

View full text Add to dashboard Cite

In this paper, we describe how the electronic rolling shutter in CMOS image sensors can be exploited using a bright, modulated light source (e.g., an inexpensive, off-the-shelf laser), to inject finegrained image disruptions. We demonstrate the attack on seven different CMOS cameras, ranging from cheap IoT to semi-professional surveillance cameras, to highlight the wide applicability of the rolling shutter attack. We model the fundamental factors affecting a rolling shutter attack in an uncontrolled setting. We then perform an exhaustive evaluation of the attack's effect on the task of object detection, investigating the effect of attack parameters. We validate our model against empirical data collected on two separate cameras, showing that by simply using information from the camera's datasheet the adversary can accurately predict the injected distortion size and optimize their attack accordingly. We find that an adversary can hide up to 75% of objects perceived by state-of-the-art detectors by selecting appropriate attack parameters. We also investigate the stealthiness of the attack in comparison to a naïve camera blinding attack, showing that common image distortion metrics can not detect the attack presence. Therefore, we present a new, accurate and lightweight enhancement to the backbone network of an object detector to recognize rolling shutter attacks. Overall, our results indicate that rolling shutter attacks can substantially reduce the performance and reliability of vision-based intelligent systems.

show abstract

MobilBye: Attacking ADAS with Camera Spoofing

Cited by 12 publications

References 4 publications

A Survey on Automated Driving System Testing: Landscapes and Trends

A Survey on Automated Driving System Testing: Landscapes and Trends

Security and Machine Learning in the Real World

They See Me Rollin’: Inherent Vulnerability of the Rolling Shutter in CMOS Image Sensors

Contact Info

Product

Resources

About