An official website of the United States government
The recent prevalence of machine learning-based techniques and smart device embedded sensors has enabled widespread human-centric sensing applications. However, these applications are vulnerable to false data injection attacks (FDIA) that alter a portion of the victim's sensory signal with forged data comprising a targeted trait. Such a mixture of forged and valid signals successfully deceives the continuous authentication system (CAS) to accept it as an authentic signal. Simultaneously, introducing a targeted trait in the signal misleads human-centric applications to generate specific targeted inference; that may cause adverse outcomes. This paper evaluates the FDIA's deception efficacy on sensor-based authentication and human-centric sensing applications simultaneously using two modalities - accelerometer, blood volume pulse signals. We identify variations of the FDIA such as different forged signal ratios, smoothed and non-smoothed attack samples. Notably, we present a novel attack detection framework named Siamese-MIL that leverages the Siamese neural networks' generalizable discriminative capability and multiple instance learning paradigms through a unique sensor data representation. Our exhaustive evaluation demonstrates Siamese-MIL's real-time execution capability and high efficacy in different attack variations, sensors, and applications.
more »
« less
Multimodal Sensors with Decoupled Sensing Mechanisms
Abstract Highly sensitive and multimodal sensors have recently emerged for a wide range of applications, including epidermal electronics, robotics, health‐monitoring devices and human–machine interfaces. However, cross‐sensitivity prevents accurate measurements of the target input signals when a multiple of them are simultaneously present. Therefore, the selection of the multifunctional materials and the design of the sensor structures play a significant role in multimodal sensors with decoupled sensing mechanisms. Hence, this review article introduces varying methods to decouple different input signals for realizing truly multimodal sensors. Early efforts explore different outputs to distinguish the corresponding input signals applied to the sensor in sequence. Next, this study discusses the methods for the suppression of the interference, signal correction, and various decoupling strategies based on different outputs to simultaneously detect multiple inputs. The recent insights into the materials' properties, structure effects, and sensing mechanisms in recognition of different input signals are highlighted. The presence of the various decoupling methods also helps avoid the use of complicated signal processing steps and allows multimodal sensors with high accuracy for applications in bioelectronics, robotics, and human–machine interfaces. Finally, current challenges and potential opportunities are discussed in order to motivate future technological breakthroughs.
more »
« less
- Award ID(s):
- 1933072
- PAR ID:
- 10371166
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Advanced Science
- Volume:
- 9
- Issue:
- 26
- ISSN:
- 2198-3844
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Medical robotics has revolutionized healthcare by enhancing precision, adaptability, and clinical outcomes. This field has further evolved with the advent of human–machine interfaces (HMIs), which facilitate seamless interactions between users and robotic systems. However, traditional HMIs rely on rigid sensing components and bulky wiring, causing mechanical mismatches that limit user comfort, accuracy, and wearability. Flexible sensors offer a transformative solution by enabling the integration of adaptable sensing technology into HMIs, enhancing overall system functionality. Further integrating artificial intelligence (AI) into these systems addresses key limitations of conventional HMI, including challenges in complex data interpretations and multimodal sensing integration. In this review, we systematically explore the convergence of flexible sensor‐based HMIs and AI for medical robotics. Specifically, we analyze core flexible sensing mechanisms, AI‐driven advancements in healthcare, and applications in prosthetics, exoskeletons, and surgical robotics. By bridging the gap between flexible sensing technologies and AI‐driven intelligence, this review presents a roadmap for developing next‐generation smart medical robotic systems, advancing personalized healthcare and adaptive human–robot interactions.more » « less
-
null (Ed.)Stimuli-responsive hydrogel strain sensors that synergize the advantages of both soft-wet hydrogels and smart functional materials have attracted rapidly increasing interest for exploring the opportunities from material design principles to emerging applications in electronic skins, health monitors, and human–machine interfaces. Stimuli-responsive hydrogel strain sensors possess smart and on-demand ability to specifically recognize various external stimuli and convert them into strain-induced mechanical, thermal, optical, and electrical signals. This review presents an up-to-date summary over the past five years on hydrogel strain sensors from different aspects, including material designs, gelation/fabrication methods, stimuli-responsive principles, and sensing performance. Hydrogel strain sensors are classified into five major categories based on the nature of the stimuli, and representative examples from each category are carefully selected and discussed in terms of structures, response mechanisms, and potential medical applications. Finally, current challenges and future perspectives of hydrogel strain sensors are tentatively proposed to stimulate more and better research in this emerging field.more » « less
-
On‐skin electronics have drawn extensive attention as they revolutionize many aspects of healthcare, motion tracking, rehabilitation, robotics, human–machine interaction, among others. Flexible and stretchable strain sensors represent one of the most explored devices for on‐skin electronics. Many printing techniques have recently emerged showing great promises for manufacturing strain sensors. Herein, it is aimed to provide a timely survey of recent advancements in printed strain sensors for on‐skin electronics. This review starts with an overview of sensing mechanisms for printed strain sensors, followed by a review of various printing techniques employed in fabricating these sensors. The materials, structures, and printing processes of representative strain sensors are discussed in detail for each printing method. Finally, potential applications of printed flexible and stretchable strain sensors are presented focusing on three areas: healthcare, sports performance monitoring, and human–machine interfaces. The review concludes with a discussion of challenges and opportunities for future research.more » « less
-
The rapid development of electronic material and sensing technology has enabled research to be conducted on liquid metal-based soft sensors. The application of soft sensors is widespread and has many applications in soft robotics, smart prosthetics, and human-machine interfaces, where these sensors can be integrated for precise and sensitive monitoring. Soft sensors can be easily integrated for soft robotic applications, where traditional sensors are incompatible with robotic applications as these types of sensors show large deformation and very flexible. These liquid-metal-based sensors have been widely used for biomedical, agricultural and underwater applications. In this research, we have designed and fabricated a novel soft sensor that yields microfluidic channel arrays embedded with liquid metal Galinstan alloy. First of all, the article presents different fabrication steps such as 3D modeling, printing, and liquid metal injection. Different sensing performances such as stretchability, linearity, and durability results are measured and characterized. The fabricated soft sensor demonstrated excellent stability and reliability and exhibited promising sensitivity with respect to different pressures and conditions.more » « less
