Model watermarking is a widely adopted mechanism for protecting deep learning (DL) model intellectual property (IP). Black-box verifiable watermarking typically involves injecting backdoors that cause the model to produce predetermined outputs for specific inputs. In contrast, white-box verifiable watermarking uses steganographic techniques to embed watermarks into weight parameters or activation values. However, the former poses new security risks, while the latter often lacks robustness against removal techniques. In this paper, we propose a latent model watermarking, constructing upon the model Division and Union operating concept, dubbed as DUO, leveraging the strengths of two watermarking methods above while eliminating each shortcoming. Once the model owner or provider embeds a watermark into the model using watermark data, the watermarked model is divided into two parts: the main model, which corresponds to the primary task and is made publicly available, and a small sub-network privately reserved by the owner. The watermark resides latently within the main model and can only be activated through the private sub-network (the reserved parameters) when they are united. Consequently, DUO does not adversely affect the performance of the main model on its primary task and does not induce any security risks, even in the presence of watermark data. We extensively validate DUO on four benchmark datasets (CIFAR-10, ImageNette, CIFAR-100, and Tiny-ImageNet) using various model architectures, including standardized ResNet and VGG. The results affirm its capability to accurately verify model ownership without compromising model accuracy. It exhibits a 100% detection accuracy on pirated/positive testing models (96 models are tested) with a 0% false positive rate on normal/negative testing models (64 models are tested). Due to its latent nature, DUO is both effective and robust, capable of withstanding a wide range of state-of-the-art watermark laundering including severe model fine-tuning and pruning. We further evaluate and demonstrate that DUO remains robust against adaptive attacks, even when both the watermark data and the reserved parameters are known to the adversary.

Personal digital data is a critical asset, and governments worldwide have enforced laws and regulations to protect data privacy. Data users have been endowed with the "right to be forgotten" (RTBF) of their data. In the course of machine learning (ML), the forgotten right requires a model provider to delete user data and its subsequent impact on ML models upon user requests. Machine unlearning (MU) emerges to address this, which has garnered ever-increasing attention from both industry and academia. Specifically, MU allows model providers to eliminate the influence of unlearned data without retraining the model from scratch, ensuring the model behaves as if it never encountered this data. While the area has developed rapidly, there is a lack of comprehensive surveys to capture the latest advancements. Recognizing this shortage, we conduct an extensive exploration to map the landscape of MU including the (fine-grained) taxonomy of unlearning algorithms under centralized and distributed settings, debate on approximate unlearning, verification and evaluation metrics, and challenges and solutions across various applications. We also focus on the motivations, challenges, and specific methods for deploying unlearning in large language models (LLMs), as well as the potential attacks targeting unlearning processes. The survey concludes by outlining potential directions for future research, hoping to serve as a beacon for interested scholars.

Abstract The implementation of Smart Airport and Airport 4.0 visions relies on the integration of automation, artificial intelligence, data science, and aviation technology to enhance passenger experiences and operational efficiency. One essential factor in the integration is the semantic segmentation of the aircraft main components (AMC) perception, which is essential to maintenance, repair, and operations in aircraft and airport operations. However, AMC segmentation has challenges from low data availability, high-quality annotation scarcity, and categorical imbalance, which are common in practical applications, including aviation. This study proposes a novel AMC segmentation solution, employing a transfer learning framework based on a sophisticated DeepLabV3 architecture optimized with a custom-designed Focal Dice Loss function. The proposed solution remarkably suppresses the categorical imbalance challenge and increases the dataset variability with manually annotated images and dynamic augmentation strategies to train a robust AMC segmentation model. The model achieved a notable intersection over union of 84.002% and an accuracy of 91.466%, significantly advancing the AMC segmentation performance. These results demonstrate the effectiveness of the proposed AMC segmentation solution in aircraft and airport operation scenarios. This study provides a pioneering solution to the AMC semantic perception problem and contributes a valuable dataset to the community, which is fundamental to future research on aircraft and airport semantic perception. Graphical abstract

Two-phase flow regime identification is an essential transdisciplinary topic that spans digital signal processing, artificial intelligence, chemical engineering, and energy. Multiphase flow systems significantly impact pipeline safety, heat transfer, and pressure drop; therefore, precisely identifying the governing flow regime is crucial for effective modeling and design. However, it is challenging due to the geometrical complexity of flow regimes in multiphase flow. With the advances in sensor measurement and machine learning, applying non-destructive tests and self-supervised learning to practical industrial problems has become technically feasible and cost-effective. This study applies a weak-supervised learning-based two-phase flow regime identification solution using a non-destructive tests ultrasonic sensor in an S-shape riser experimental bed by proposing a self-supervised feature extraction algorithm. The proposed self-supervised feature extraction algorithm reduces time/labor consumption and human error in data annotation using SSL, which provides full supervision without manual annotation. The self-supervised feature extraction algorithm uses a bottlenecked neural network and encoder-decoder structure to extract compact features. The self-supervised feature extraction algorithm performance is evaluated using an established convolutional neural network-based classifier. The source data was collected from a 10×50 meter riser experimental rig. The dataset is made available to the community as part of this study. The performance of the approach is comparable with state-of-the-art methods and is also the first successful attempt to apply self-supervised learning to multiphase flow regime ultrasonic signal identification. This study achieved 98.84%, 0.000663, 0.00312, and 7.71×105 in accuracy, root mean square error, categorical cross-entropy, and model complexity, respectively. The practical experiment justifies the robustness, fairness, and practicability in the practical application environment. The proposed self-supervised feature extraction brings new approaches and inspirations for the feature extraction step in identifying a two-phase flow regime, and it will be beneficial to generalize this study in different riser shapes in the future.

The problem of classifying gas-liquid two-phase flow regimes from ultrasonic signals is considered. A new method, belt-shaped features (BSFs), is proposed for performing feature extraction on the preprocessed data. A convolutional neural network (CNN/ConvNet)-based classifier is then applied to categorize into one of the four flow regimes: 1) annular; 2) churn; 3) slug; or 4) bubbly. The proposed ConvNet classifier includes multiple stages of convolution and pooling layers, which both decrease the dimension and learn the classification features. Using experimental data collected from an industrial-scale multiphase flow facility, the proposed ConvNet classifier achieved 97.40%, 94.57%, and 94.94% accuracy, respectively, for the training set, testing set, and validation set. These results demonstrate the applicability of the BSF features and the ConvNet classifier for flow regime classification in industrial applications.

Swarm attestation, as an important branch of Remote Attestation (RA), enables a trusted party (verifier) to verify the security states of multiple devices (provers) in a large network (swarm) simultaneously via a challenge-response mechanism. However, swarm attestation suffers from significant redundancy overhead since all devices in the swarm need to be attested in each attestation round. Besides, it faces challenges such as verifier-impersonation Denial of Service (DoS) attacks, highly dynamic networks, transient & self-relocating malware, and Time-Of-Check-Time-Of-Use (TOCTOU) attacks. In this paper, considering not only the detection accuracy but also the privacy of swarm owners in real Internet of Things (IoT) scenarios, we propose an Automatic Federated Swarm Attestation scheme (FeSA). Under this scheme, we design a federated-learning-based automatic swarm attestation protocol that enables theverifiersto identify the suspicious devices by a neural network model and then attest them. To the best of our knowledge, this is the first scheme to apply a federated learning method to RA, ruling out the redundancy attestation rounds while preserving data privacy. The FeSA redesigns the interaction model of RA by a challenge-query mechanism to reduce the overhead of an individual device to a constant. In order to evaluate our scheme, we first set up a smart office environment with 12 types of smart IoT devices for real-world data collection up to 21 days. Based on the real dataset, we demonstrate that FeSA can indeed identify the compromised IoT devices while reducing redundancy. We further simulate large-scale swarms of up to 1,000,000 devices to validate the efficiency of FeSA in large-scale swarms. Last, the security analysis proves the ability of FeSA to resist various attacks.

An Internet of Things (IoT) system generally contains thousands of heterogeneous devices which often operate in swarms-large, dynamic, and self-organizing networks. Remote attestation is an important cornerstone for the security of these IoT swarms, as it ensures the software integrity of swarm devices and protects them from attacks. However, current attestation schemes suffer from single point of failure verifier. In this paper, we propose an Efficient and Secure Distributed Remote Attestation (ESDRA) scheme for IoT swarms. We present the first many-to-one attestation scheme for device swarms, which reduces the possibility of single point of failure verifier. Moreover, we utilize distributed attestation to verify the integrity of each node and apply accusation mechanism to report the invaded nodes, which makes ESDRA much easier to feedback the certain compromised nodes and reduces the run-time of attestation. We analyze the security of ESDRA and do some simulation experiments to show its practicality and efficiency. Especially, ESDRA can significantly reduce the attestation time and has a better performance in the energy consumption comparing with list-based attestation schemes.