Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses

Deng, Yao; Zhang, Tiehua; Lou, Guannan; Zheng, Xi; Jin, Jiong; Han, Qing‐Long

doi:10.1109/tii.2021.3071405

Cited by 99 publications

(33 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Before this paper, a few AD security-related surveys have been published [20][21][22][23], but none of them focus on the emerging semantic AD AI research space (i.e., our scope defined in §II-C). For example, Kim et al [20] and Ren et al [21] focus on AD-related sensor/hardware security and in-vehicle network security, instead of AD AI components.…”

Section: Related Workmentioning

confidence: 99%

“…For example, Kim et al [20] and Ren et al [21] focus on AD-related sensor/hardware security and in-vehicle network security, instead of AD AI components. Qayyum et al [23] and Deng et al [22] touched upon the security of AI components in AD, but did not focus on the works that addressed the semantic AI security challenges (e.g., most of the included works are on generic AI and sensor security without studying impacts on AD AI behaviors). In fact, Deng et al [22] considers the semantic AD AI security as a future direction.…”

Section: Related Workmentioning

confidence: 99%

“…However, to the best of our knowledge, so far there is no comprehensive systematization of this emerging research space. There are surveys related to AD security, but they either did not focus on AD AI components (e.g., on sensor/hardware [20], in-vehicle network [21]), or touched upon AD AI components but did not focus on the works that addressed the semantic AI security challenges above [22,23]. Since (1) the latter ones are much more semantically and thus practically meaningful for AD systems, (2) now a substantial amount of them have appeared (over 50 as in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

SoK: On the Semantic AI Security in Autonomous Driving

Shen¹,

Wang²,

Wan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Autonomous Driving (AD) systems rely on AI components to make safety and correct driving decisions. Unfortunately, today's AI algorithms are known to be generally vulnerable to adversarial attacks. However, for such AI component-level vulnerabilities to be semantically impactful at the system level, it needs to address non-trivial semantic gaps both (1) from the system-level attack input spaces to those at AI component level, and (2) from AI component-level attack impacts to those at the system level. In this paper, we define such research space as semantic AI security as opposed to generic AI security. Over the past 5 years, increasingly more research works are performed to tackle such semantic AI security challenges in AD context, which has started to show an exponential growth trend. However, to the best of our knowledge, so far there is no comprehensive systematization of this emerging research space.In this paper, we thus perform the first systematization of knowledge of such growing semantic AD AI security research space. In total, we collect and analyze 53 such papers, and systematically taxonomize them based on research aspects critical for the security field such as the attack/defense targeted AI component, attack/defense goal, attack vector, attack knowledge, defense deployability, defense robustness, and evaluation methodologies. We summarize 6 most substantial scientific gaps observed based on quantitative comparisons both vertically among existing AD AI security works and horizontally with security works from closely-related domains. With these, we are able to provide insights and potential future directions not only at the design level, but also at the research goal, methodology, and community levels. To address the most critical scientific methodology-level gap, we take the initiative to develop an open-source, uniform, and extensible system-driven evaluation platform, named PASS, for the semantic AD AI security research community. We also use our implemented platform prototype to showcase the capabilities and benefits of such a platform using representative semantic AD AI attacks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

SoK: On the Semantic AI Security in Autonomous Driving

Shen¹,

Wang²,

Wan³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…As well as various sensors for detecting the outside world, the vehicle will be equipped with on-board computer processors and electronic-oriented memory technology, and can communicate with the cloud via a communication device [363]. Besides data communication, edge-cloud collaborative learning techniques will further enhance autonomous driving on safety, functionality, and privacy [364]. Initially trained on clouds, edge machine learning models (cloud → edge) can interpret real-time raw data, make decisions based on the derived insights, and learn from the feedback from real-time road conditions.…”

Section: Auto-drivingmentioning

confidence: 99%

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI

Yao¹,

Zhang²,

Yang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Influenced by the great success of deep learning via cloud computing and the rapid development of edge chips, research in artificial intelligence (AI) has shifted to both of the computing paradigms, i.e., cloud computing and edge computing. In recent years, we have witnessed significant progress in developing more advanced AI models on cloud servers that surpass traditional deep learning models owing to model innovations (e.g., Transformers, Pretrained families), explosion of training data and soaring computing capabilities. However, edge computing, especially edge and cloud collaborative computing, are still in its infancy to announce their success due to the resource-constrained IoT scenarios with very limited algorithms deployed. In this survey, we conduct a systematic review for both cloud and edge AI. Specifically, we are the first to set up the collaborative learning mechanism for cloud and edge modeling with a thorough review of the architectures that enable such mechanism. We also discuss potentials and practical experiences of some on-going advanced edge AI topics including pretraining models, graph neural networks and reinforcement learning. Finally, we discuss the promising directions and challenges in this field.

show abstract

“…Although the image classification model provides great convenience for users, the inherent fragile of deep learning is a weakness of the service. Recent studies [12,13] have shown that an attacker can create adversarial samples by adding small disturbances to the original data. e disturbances are very small, and they are almost invisible to the human eye.…”

Section: Introductionmentioning

confidence: 99%

FNet: A Two-Stream Model for Detecting Adversarial Attacks against 5G-Based Deep Learning Services

Feng

Jiao

et al. 2021

Security and Communication Networks

Self Cite

View full text Add to dashboard Cite

With the extensive application of artificial intelligence technology in 5G and Beyond Fifth Generation (B5G) networks, it has become a common trend for artificial intelligence to integrate into modern communication networks. Deep learning is a subset of machine learning and has recently led to significant improvements in many fields. In particular, many 5G-based services use deep learning technology to provide better services. Although deep learning is powerful, it is still vulnerable when faced with 5G-based deep learning services. Because of the nonlinearity of deep learning algorithms, slight perturbation input by the attacker will result in big changes in the output. Although many researchers have proposed methods against adversarial attacks, these methods are not always effective against powerful attacks such as CW. In this paper, we propose a new two-stream network which includes RGB stream and spatial rich model (SRM) noise stream to discover the difference between adversarial examples and clean examples. The RGB stream uses raw data to capture subtle differences in adversarial samples. The SRM noise stream uses the SRM filters to get noise features. We regard the noise features as additional evidence for adversarial detection. Then, we adopt bilinear pooling to fuse the RGB features and the SRM features. Finally, the final features are input into the decision network to decide whether the image is adversarial or not. Experimental results show that our proposed method can accurately detect adversarial examples. Even with powerful attacks, we can still achieve a detection rate of 91.3%. Moreover, our method has good transferability to generalize to other adversaries.

show abstract

Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defenses

Cited by 99 publications

References 77 publications

SoK: On the Semantic AI Security in Autonomous Driving

SoK: On the Semantic AI Security in Autonomous Driving

Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI

FNet: A Two-Stream Model for Detecting Adversarial Attacks against 5G-Based Deep Learning Services

Contact Info

Product

Resources

About