About this Research Topic
The rapid advancement of intelligent camera-based functionalities within smart cyber-physical systems (CPS) and the Internet-of-Things (IoT) has brought about unprecedented challenges in security and privacy. As nano-scale devices become more widespread, these systems are increasingly vulnerable to emerging attack vectors, particularly those targeting the processing of image and video data. Modern machine learning (ML) systems employed in visual data processing are significantly threatened by adversarial and backdoor attacks. In these scenarios, deliberate manipulations in images exploit the inherent vulnerabilities of ML models, potentially compromising system performance, decision-making processes, and overall system integrity. The growing sophistication of these threats underscores the urgent need for advanced defense mechanisms and robust security strategies to protect against them.
This Research Topic aims to gather cutting-edge research addressing the security and privacy challenges faced by intelligent systems in CPS and IoT. The primary goal is to explore innovative defense and obfuscation strategies that can enhance the resilience of systems processing image and video data. We are particularly interested in advancing the understanding of safeguarding ML models against adversarial and backdoor attacks, especially in critical applications such as depth estimation, object detection, and classification. Another key goal is to investigate the specific threats posed to autonomous systems and mobile robots, identifying strategies to protect these systems from evolving security risks. By bringing together contributions from researchers and practitioners, this Research Topic aspires to shape the future of security measures in CPS and IoT, ensuring that these systems remain safe and effective in an increasingly hostile environment.
We encourage submissions that provide a comprehensive overview of strategies designed to safeguard intelligent systems in CPS and IoT from the rapidly evolving security and privacy landscape. Case studies focusing on the security of systems processing image and video data are particularly welcome. Topics of interest include, but are not limited to, the following:
• Adversarial and backdoor attack detection,
• Defense mechanisms for ML models,
• Privacy-preserving techniques
• Security strategies
All being applied in autonomous systems and mobile robots.
Submissions should offer novel insights, practical implementations, or comprehensive overviews of current and emerging security threats. We encourage authors to emphasize both theoretical advancements and practical applications, offering valuable perspectives for researchers and practitioners alike. This Research Topic is linked to the tutorial "ML in Autonomous Systems and Mobile Robots: Security and Privacy Issues for ML" at the IROS 2024 conference. We encourage submissions which were previously published as conference proceedings, however, they should be extended to include 30% original content to be considered.
This Research Topic aims to gather cutting-edge research addressing the security and privacy challenges faced by intelligent systems in CPS and IoT. The primary goal is to explore innovative defense and obfuscation strategies that can enhance the resilience of systems processing image and video data. We are particularly interested in advancing the understanding of safeguarding ML models against adversarial and backdoor attacks, especially in critical applications such as depth estimation, object detection, and classification. Another key goal is to investigate the specific threats posed to autonomous systems and mobile robots, identifying strategies to protect these systems from evolving security risks. By bringing together contributions from researchers and practitioners, this Research Topic aspires to shape the future of security measures in CPS and IoT, ensuring that these systems remain safe and effective in an increasingly hostile environment.
We encourage submissions that provide a comprehensive overview of strategies designed to safeguard intelligent systems in CPS and IoT from the rapidly evolving security and privacy landscape. Case studies focusing on the security of systems processing image and video data are particularly welcome. Topics of interest include, but are not limited to, the following:
• Adversarial and backdoor attack detection,
• Defense mechanisms for ML models,
• Privacy-preserving techniques
• Security strategies
All being applied in autonomous systems and mobile robots.
Submissions should offer novel insights, practical implementations, or comprehensive overviews of current and emerging security threats. We encourage authors to emphasize both theoretical advancements and practical applications, offering valuable perspectives for researchers and practitioners alike. This Research Topic is linked to the tutorial "ML in Autonomous Systems and Mobile Robots: Security and Privacy Issues for ML" at the IROS 2024 conference. We encourage submissions which were previously published as conference proceedings, however, they should be extended to include 30% original content to be considered.
Keywords: Machine Learning, Security, Privacy-Preserving Techniques, Autonomous Systems, Mobile Robots, Adversarial Attacks, Backdoor Attacks, Defense Mechanisms
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
