Security of AI-Driven Sensing Systems
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".
Deadline for manuscript submissions: 31 December 2026 | Viewed by 120
Special Issue Editor
Interests: security and privacy of distributed learning; (large language model) LLM security; Web3 security; biometric security
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Artificial Intelligence (AI) has become a cornerstone of modern innovation, powering intelligent applications in domains such as autonomous driving, healthcare, smart manufacturing, and cyber defense. In most of these scenarios, AI models are deeply embedded in sensing pipelines, transforming raw measurements from cameras, LiDAR, radar, biosensors, wearables, industrial sensors, and IoT devices into high-level perception and control decisions. As AI-driven systems increasingly permeate critical sensor-centric infrastructures, they also introduce new and complex security vulnerabilities. Malicious actors can exploit weaknesses in sensor data acquisition, edge and cloud processing, model architectures, and deployment frameworks, giving rise to emerging threats such as data poisoning on sensor streams, adversarial perturbations and spoofing of physical signals, model inversion, and large-scale misinformation based on sensed data. Ensuring the security, privacy, and trustworthiness of AI-enabled sensing pipelines has thus become a central challenge for building resilient and responsible cyber-physical and IoT ecosystems.
This Special Issue aims to bring together cutting-edge research addressing the security, privacy, robustness, and safety challenges of AI-driven sensing applications and systems. We particularly welcome contributions that involve real sensor data, sensing devices and platforms, or sensor-rich environments (e.g., IoT, industrial control systems, smart cities, intelligent transportation, and healthcare monitoring). We invite original research that explores theoretical foundations, practical defense mechanisms, trustworthy design principles, and real-world implementations, with a clear connection to sensing technologies or sensor-based systems. The goal is to foster interdisciplinary collaboration across artificial intelligence, cybersecurity, and system/sensor engineering communities, and to advance the development of safe, explainable, and reliable AI technologies capable of withstanding evolving adversarial threats in sensor-driven environments.
Topics of interest include (but are not limited to):
- Adversarial attacks and defenses in AI systems
- Privacy-preserving machine learning and federated learning
- Trustworthy and explainable AI for secure decision-making
- Security of large language models and generative AI
- Model inversion, extraction, and membership inference attacks
- Data poisoning and backdoor attacks in training pipelines
- Secure deployment and lifecycle management of AI models
- AI-based intrusion detection and threat intelligence systems
- Blockchain and distributed ledger technologies for AI trust
- Secure and privacy-aware multi-agent or autonomous systems
- AI security in cloud-edge-end collaborative environments
- Formal verification and reliability assurance of AI systems
- Human-in-the-loop and governance mechanisms for AI safety
- Secure data sharing, knowledge distillation, and domain adaptation for sensor deployments
- Real-world case studies, benchmarks, and testbeds for AI-driven cyber defense in sensing environments
- AI security in cloud–edge–end collaborative sensing environments
- AI-based intrusion detection and threat intelligence for sensor networks and IoT systems
- Data poisoning and backdoor attacks in sensor data collection and training pipelines
Dr. Cong Wu
Guest Editor
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- intelligent systems security
- cyber threat resilience
- AI and ML in cybersecurity
- privacy-preserving technology
- blockchain and IoT security
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.
Further information on MDPI's Special Issue policies can be found here.
