CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection

Hu, Shanshan; Zhang, Yang; Laha, Sumit; Sharma, Ankit Kumar; Foroosh, Hassan

doi:10.1109/icpr48806.2021.9413194

Cited by 6 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Physical-world attack vectors: posters [18,37,54], and camouflages [56,60,63], or displayed by projectors [66] and digital billboards [57].…”

Section: B Systematization Of Semantic Ad Ai Attacksmentioning

confidence: 99%

“…Existing attacks have applied this attack vector on various objects such as STOP signs [18,26,37,54], road surfaces [78,79], vehicles [56,60,63,71], clothes [61,62], physical billboards [94]. To disguise as benign looking, a few attacks also constrain the texture perturbations to improve the attack stealthiness [60,78,79].…”

Section: B Systematization Of Semantic Ad Ai Attacksmentioning

confidence: 99%

“…Prior gray-box attacks all assume the lack of knowledge of AI model internals such as weights. However, some works still require confidence scores in the model outputs [56,[63][64][65]71,79,83,84], and some require detailed sensor parameters [65,67,89].…”

Section: Sensor Attack Vectorsmentioning

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

“…Physical-world attack vectors: posters [18,37,54], and camouflages [56,60,63], or displayed by projectors [66] and digital billboards [57].…”

Section: B Systematization Of Semantic Ad Ai Attacksmentioning

confidence: 99%

Section: B Systematization Of Semantic Ad Ai Attacksmentioning

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

“…Targeted Component Component-level System-level Lu et al [27] object detection ✓ Eykholt et al [12] object detection ✓ Chen et al [7] object detection ✓ Zhao et al [48] object detection ✓ Xiao et al [44] object detection ✓ Zhang et al [47] object detection ✓ Nassi et al [30] object detection ✓ ✓ Man et al [28] object detection ✓ Hong et al [17] object detection ✓ Huang et al [19] object detection ✓ Wu et al [43] object detection ✓ Xu et al [45] object detection ✓ Hu et al [18] object detection ✓ Hamdi et al [16] object detection ✓ Ji et al [21] object detection ✓ Lovisotto et al [26] object detection ✓ Köhler et al [23] object detection ✓ Wang et al [40] object detection ✓ Zolfi et al [51] object detection ✓ Wang et al [41] object detection ✓ Zhu et al [50] object detection ✓ Wang et al [42] Traffic light detection ✓ Tang et al [39] Traffic light detection ✓ those in Table I), a component-level success rate of up to 98% can still be not enough to affect object tracking results. Thus, we believe that such current general lack of systemlevel evaluation is a critical scientific methodology-level gap that should be addressed as soon as possible.…”

Section: Papermentioning

confidence: 99%

PASS: A System-Driven Evaluation Platform for Autonomous Driving Safety and Security

Hu¹,

Shen²,

Guo³

et al. 2022

Proceedings Fourth International Workshop on Automotive and Autonomous Vehicle Security

View full text Add to dashboard Cite

Safety and security play critical roles for the success of Autonomous Driving (AD) systems. Since AD systems heavily rely on AI components, the safety and security research of such components has also received great attention in recent years. While it is widely recognized that AI component-level (mis)behavior does not necessarily lead to AD system-level impacts, most of existing work still only adopts component-level evaluation. To fill such critical scientific methodology-level gap from component-level to real system-level impact, a system-driven evaluation platform jointly constructed by the community could be the solution. In this paper, we present P ASS (Platform for Auto-driving Safety and Security), a system-driven evaluation prototype based on simulation. By sharing our platform building concept and preliminary efforts, we hope to call on the community to build a uniform and extensible platform to make AI safety and security work sufficiently meaningful at the system level.

show abstract

Attacking Object Detector by Simultaneously Learning Perturbations and Locations

Wang

Zhang

2022

Neural Process Lett

View full text Add to dashboard Cite

CCA: Exploring the Possibility of Contextual Camouflage Attack on Object Detection

Cited by 6 publications

References 32 publications

SoK: On the Semantic AI Security in Autonomous Driving

SoK: On the Semantic AI Security in Autonomous Driving

PASS: A System-Driven Evaluation Platform for Autonomous Driving Safety and Security

Attacking Object Detector by Simultaneously Learning Perturbations and Locations

Contact Info

Product

Resources

About