Related papers: SudokuSens: Enhancing Deep Learning Robustness for…

The Internet of Things (IoT) provides applications and services that would otherwise not be possible. However, the open nature of IoT make it vulnerable to cybersecurity threats. Especially, identity spoofing attacks, where an adversary…

The rapid expansion of the Internet of Things (IoT) has raised increasing concern about targeted cyber attacks. Previous research primarily focused on static Intrusion Detection Systems (IDSs), which employ offline training to safeguard IoT…

Crowdsensing is a promising sensing paradigm for smart city applications (e.g., traffic and environment monitoring) with the prevalence of smart mobile devices and advanced network infrastructure. Meanwhile, as tasks are performed by…

Deep learning has been broadly applied to imaging in scattering applications. A common framework is to train a descattering network for image recovery by removing scattering artifacts. To achieve the best results on a broad spectrum of…

Our ability to synthesize sensory data that preserves specific statistical properties of the real data has had tremendous implications on data privacy and big data analytics. The synthetic data can be used as a substitute for selective real…

While synthetic tabular data generation using Deep Generative Models (DGMs) offers a compelling solution to data scarcity and privacy concerns, their effectiveness relies on the availability of substantial training data, often lacking in…

Data sensing and gathering is an essential task for various information-driven services in smart cities. On the one hand, Internet of Things (IoT) sensors can be deployed at certain fixed locations to capture data reliably but suffer from…

In automated crop protection tasks such as weed control, disease diagnosis, and pest monitoring, deep learning has demonstrated significant potential. However, these advanced models rely heavily on high-quality, diverse datasets, often…

As the Internet of Things (IoT) continues to grow, cyberattacks are becoming increasingly common. The security of IoT networks relies heavily on intrusion detection systems (IDSs). The development of an IDS that is accurate and efficient is…

A challenge in training discriminative models like neural networks is obtaining enough labeled training data. Recent approaches use generative models to combine weak supervision sources, like user-defined heuristics or knowledge bases, to…

High-quality training data is essential for enhancing the robustness of object detection models. Within the maritime domain, obtaining a diverse real image dataset is particularly challenging due to the difficulty of capturing sea images…

Voice assistants are now widely available, and to activate them a keyword spotting (KWS) algorithm is used. Modern KWS systems are mainly trained using supervised learning methods and require a large amount of labelled data to achieve a…

We propose self-adaptive training -- a unified training algorithm that dynamically calibrates and enhances training processes by model predictions without incurring an extra computational cost -- to advance both supervised and…

This paper introduces ROSAR, a novel framework enhancing the robustness of deep learning object detection models tailored for side-scan sonar (SSS) images, generated by autonomous underwater vehicles using sonar sensors. By extending our…

Data scaling and standardized evaluation benchmarks have driven significant advances in natural language processing and computer vision. However, robotics faces unique challenges in scaling data and establishing evaluation protocols.…

In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent, development, these two fields have evolved distinct architectural paradigms: the…

We present PSEUDo, an adaptive feature learning technique for exploring visual patterns in multi-track sequential data. Our approach is designed with the primary focus to overcome the uneconomic retraining requirements and inflexible…

The fact that robots are getting deployed more often in dynamic environments, together with the increasing complexity of their software systems, raises the need for self-adaptive approaches. In these environments robotic software systems…

Timeseries partitioning is an essential step in most machine-learning driven, sensor-based IoT applications. This paper introduces a sample-efficient, robust, time-series segmentation model and algorithm. We show that by learning a…

In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition (i.e., less generalizable), so that one cannot prevent a model from co-adapting on such…