Neural style transfer (NST) generates new images by combining the style of one image with the content of another. However, unauthorized NST can exploit artwork, raising concerns about artists' rights and motivating the development of proactive protection methods. We propose Locally Adaptive Adversarial Color Attack (LAACA), enabling artists to conveniently protect their work from unauthorized NST by pre-processing the artwork image before public release, providing content-independent protection regardless of which content image it may later be combined with. LAACA introduces adaptive perturbations that significantly degrade NST quality while maintaining the visual integrity of the original image. We also develope LAACAv2, which resists the current SOTA adversarial perturbation removal method - SDEdit-based adversarial purification. Additionally, we introduce the Aesthetic Color Distance Metric (ACDM) to better evaluate color-sensitive tasks like NST. Extensive experiments across various NST techniques demonstrate our methods outperform baselines in structural similarity, color preservation, and perceptual quality. User studies with both general users and art experts confirm the practical applicability of our approach, addressing the social trust crisis in the art community while advancing adversarial machine learning at the intersection of art, technology, and intellectual property rights.

Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape of adversarial techniques, revealing their dual nature as both sophisticated security threats and valuable defensive tools. We provide a systematic analysis of adversarial attack methodologies across three primary domains: pixel-space attacks, physically realizable attacks, and latent-space attacks. Our investigation traces the technical evolution from early gradient-based methods such as FGSM and PGD to sophisticated optimization techniques incorporating momentum, adaptive step sizes, and advanced transferability mechanisms. We examine how physically realizable attacks have successfully bridged the gap between digital vulnerabilities and real-world threats through adversarial patches, 3D textures, and dynamic optical perturbations. Additionally, we explore the emergence of latent-space attacks that leverage semantic structure in internal representations to create more transferable and meaningful adversarial examples. Beyond traditional offensive applications, we investigate the constructive use of adversarial techniques for vulnerability assessment in biometric authentication systems and protection against malicious generative models. Our analysis reveals critical research gaps, particularly in neural style transfer protection and computational efficiency requirements. This survey contributes a comprehensive taxonomy, evolution analysis, and identification of future research directions, aiming to advance understanding of adversarial vulnerabilities and inform the development of more robust and trustworthy computer vision systems.

Recent advancements in Latent Diffusion Models (LDMs) have revolutionized image synthesis and manipulation, raising significant concerns about data misappropriation and intellectual property infringement. While adversarial attacks have been extensively explored as a protective measure against such misuse of generative AI, current approaches are severely limited by their heavy reliance on model-specific knowledge and substantial computational costs. Drawing inspiration from the posterior collapse phenomenon observed in VAE training, we propose the Posterior Collapse Attack (PCA), a novel framework for protecting images from unauthorized manipulation. Through comprehensive theoretical analysis and empirical validation, we identify two distinct collapse phenomena during VAE inference: diffusion collapse and concentration collapse. Based on this discovery, we design a unified loss function that can flexibly achieve both types of collapse through parameter adjustment, each corresponding to different protection objectives in preventing image manipulation. Our method significantly reduces dependence on model-specific knowledge by requiring access to only the VAE encoder, which constitutes less than 4% of LDM parameters. Notably, PCA achieves prompt-invariant protection by operating on the VAE encoder before text conditioning occurs, eliminating the need for empty prompt optimization required by existing methods. This minimal requirement enables PCA to maintain adequate transferability across various VAE-based LDM architectures while effectively preventing unauthorized image editing. Extensive experiments show PCA outperforms existing techniques in protection effectiveness, computational efficiency (runtime and VRAM), and generalization across VAE-based LDM variants. Our code is available at https://github.com/ZhongliangGuo/PosteriorCollapseAttack.

In this paper, the percolation properties of higher-order networks that have non-trivial clustering and subgraph-based assortative mixing (the tendency of vertices to connect to other vertices based on subgraph joint degree) are examined. Our analytical method is based on generating functions and is exact for the networks we model. We also propose a Monte Carlo graph generation algorithm to draw random networks from the ensemble of graphs with fixed statistics. The proposed model is used to understand the effect that network microstructure has, through the arrangement of inter-subgraph clustering, on the global connective properties of the network. We find that even in k-regular networks, with fixed joint degree distributions and clustering coefficients, the arrangement of clustering has a non-trivial influence on the percolation properties of the network. We find that subgraph disassortativity increases the percolation threshold, whilst assortativity among subgraphs decreases and broadens the transition. Finally, we use an edge disjoint clique cover to represent empirical networks using our formulation, finding the resultant model offers a significant improvement over edge-based theory.

The rapid development of heterogeneous networks has proposed new challenges to the long-standing link prediction problem. Existing models trained on the verified edge samples from different types usually learn type-specific knowledge, and their type-specific predictions may be contradictory for unverified edge samples with uncertain types. This challenge is termed edge-type disturbance in link prediction in heterogeneous networks. To address this challenge, we develop a disturbance-resilient prediction method ( DRPM ) comprising a structural characterizer, a type differentiator, and a resilient predictor. The structural characterizer is responsible for learning edge representations for link prediction. Concurrently, the type differentiator distinguishes type-specific edge representations to generate diverse type experts while maximizing their link prediction performances on specific types. Furthermore, the resilient predictor evaluates the reliability weights of different type experts to develop a resilient prediction mechanism to aggregate discriminable predictions. Extensive experiments conducted on various real-world datasets demonstrate the importance of the explainable introduction of the edge-type disturbance and the superiority of DRPM over state-of-the-art methods.

This paper introduces significant enhancements to RepoSim4Py and RepoSnipy, advanced semantic tools for deep analysis of software repositories. RepoSim4Py commandline toolbox now supports multi-level embedding, encompassing code, documentation, requirements, README, and comprehensive repository analysis, which enable the understanding of repository dynamics. Concurrently, RepoSnipy webbased search engine facilitates sophisticated repository similarity searches and introduces clustering based on both repository tags (topic_cluster) and code embeddings (code_cluster). We also introduce SimilarityCal, a novel binary classification model trained on these clusters, to predict and quantify repository similarities with high accuracy. These developments provide researchers and developers with powerful tools to navigate the complex landscape of software repositories, improving efficiency in software development and fostering innovation through better reuse of existing resources.

In this paper, we tackle the challenge of white-box false positive adversarial attacks on contrastive loss based offline handwritten signature verification models. We propose a novel attack method that treats the attack as a style transfer between closely related but distinct writing styles. To guide the generation of deceptive images, we introduce two new loss functions that enhance the attack success rate by perturbing the Euclidean distance between the embedding vectors of the original and synthesized samples, while ensuring minimal perturbations by reducing the difference between the generated image and the original image. Our method demonstrates state-of-the-art performance in white-box attacks on contrastive loss based offline handwritten signature verification models, as evidenced by our experiments. The key contributions of this paper include a novel false positive attack method, two new loss functions, effective style transfer in handwriting styles, and superior performance in white-box false positive attacks compared to other white-box attack methods.

Neural style transfer (NST) generates new images by combining the style of one image with the content of another. However, unauthorized NST can exploit artwork, raising concerns about artists' rights and motivating the development of proactive protection methods. We propose Locally Adaptive Adversarial Color Attack (LAACA), empowering artists to protect their artwork from unauthorized style transfer by processing before public release. By delving into the intricacies of human visual perception and the role of different frequency components, our method strategically introduces frequency-adaptive perturbations in the image. These perturbations significantly degrade the generation quality of NST while maintaining an acceptable level of visual change in the original image, ensuring that potential infringers are discouraged from using the protected artworks, because of its bad NST generation quality. Additionally, existing metrics often overlook the importance of color fidelity in evaluating color-mattered tasks, such as the quality of NST-generated images, which is crucial in the context of artistic works. To comprehensively assess the color-mattered tasks, we propose the Aesthetic Color Distance Metric (ACDM), designed to quantify the color difference of images pre- and post-manipulations. Experimental results confirm that attacking NST using LAACA results in visually inferior style transfer, and the ACDM can efficiently measure color-mattered tasks. By providing artists with a tool to safeguard their intellectual property, our work relieves the socio-technical challenges posed by the misuse of NST in the art community.

Heterogeneous social networks, which are characterized by diverse interaction types, have resulted in new challenges for missing link prediction. Most deep learning models tend to capture type-specific features to maximize the prediction performances on specific link types. However, the types of missing links are uncertain in heterogeneous social networks; this restricts the prediction performances of existing deep learning models. To address this issue, we propose a multi-type transferable method (MT TM) for missing link prediction in heterogeneous social networks, which exploits adversarial neural networks to remain robust against type differences. It comprises a generative predictor and a discriminative classifier. The generative predictor can extract link representations and predict whether the unobserved link is a missing link. To generalize well for different link types to improve the prediction performance, it attempts to deceive the discriminative classifier by learning transferable feature representations among link types. In order not to be deceived, the discriminative classifier attempts to accurately distinguish link types, which indirectly helps the generative predictor judge whether the learned feature representations are transferable among link types. Finally, the integrated MTT M is constructed on this minimax two-player game between the generative predictor and discriminative classifier to predict missing links based on transferable feature representations among link types. Extensive experiments show that the proposed MTT M can outperform state-of-the-art baselines for missing link prediction in heterogeneous social networks.

Sensor-based human activity recognition (HAR), with the ability to recognise human activities from wearable or embedded sensors, has been playing an important role in many applications including personal health monitoring, smart home, and manufacturing. The real-world, long-term deployment of these HAR systems drives a critical research question: how to evolve the HAR model automatically over time to accommodate changes in an environment or activity patterns. This paper presents an online continual learning (OCL) scenario for HAR, where sensor data arrives in a streaming manner which contains unlabelled samples from already learnt activities or new activities. We propose a technique, OCL-HAR, making a real-time prediction on the streaming sensor data while at the same time discovering and learning new activities. We have empirically evaluated OCL-HAR on four third-party, publicly available HAR datasets. Our results have shown that this OCL scenario is challenging to state-of-the-art continual learning techniques that have significantly underperformed. Our technique OCL-HAR has consistently outperformed them in all experiment setups, leading up to 0.17 and 0.23 improvements in micro and macro F1 scores.

In this paper we examine the percolation properties of higher-order networks that have non-trivial clustering and subgraph-based assortative mixing (the tendency of vertices to connect to other vertices based on subgraph joint degree). Our analytical method is based on generating functions. We also propose a Monte Carlo graph generation algorithm to draw random networks from the ensemble of graphs with fixed statistics. We use our model to understand the effect that network microstructure has, through the arrangement of clustering, on the global properties. Finally, we use an edge disjoint clique cover to represent empirical networks using our formulation, finding the resultant model offers a significant improvement over edge-based theory.

The advances of sensing and computing technologies pave the way to develop novel applications and services for wearable devices. For example, wearable devices measure heart rate, which accurately reflects the intensity of physical exercise. Therefore, heart rate prediction from wearable devices benefits users with optimization of the training process. Conventionally, Cloud collects user data from wearable devices and conducts inference. However, this paradigm introduces significant privacy concerns. Federated learning is an emerging paradigm that enhances user privacy by remaining the majority of personal data on users’ devices. In this paper, we propose a statistically sound, Bayesian inference federated learning for heart rate prediction with autoregression with exogenous variable (ARX) model. The proposed privacy-preserving method achieves accurate and robust heart rate prediction. To validate our method, we conduct extensive experiments with real-world outdoor running exercise data collected from wearable devices.

Recently, dynamic social network research has attracted a great amount of attention, especially in the area of anomaly analysis that analyzes the anomalous change in the evolution of dynamic social networks. However, most of the current research focused on anomaly analysis of the macro representation of dynamic social networks and failed to analyze the nodes that have anomalous structural changes at a micro level. To identify and evaluate anomalous structural change-based nodes in generalized dynamic social networks that only have limited structural information, this research considers undirected and unweighted graphs and develops a multiple-neighbor superposition similarity method (), which mainly consists of a multiple-neighbor range algorithm () and a superposition similarity fluctuation algorithm (). introduces observation nodes, characterizes the structural similarities of nodes within multiple-neighbor ranges, and proposes a new multiple-neighbor similarity index on the basis of extensional similarity indices. Subsequently, maximally reflects the structural change of each node, using a new superposition similarity fluctuation index from the perspective of diverse multiple-neighbor similarities. As a result, based on and , not only identifies anomalous structural change-based nodes by detecting the anomalous structural changes of nodes but also evaluates their anomalous degrees by quantifying these changes. Results obtained by comparing with state-of-the-art methods via extensive experiments show that can accurately identify anomalous structural change-based nodes and evaluate their anomalous degrees well.

Human activity recognition plays a significant role in enabling pervasive applications as it abstracts low-level noisy sensor data into high-level human activities, which applications can respond to. With more and more activity-aware applications deployed in real-world environments, a research challenge emerges-discovering and learning new activities that have not been pre-defined or observed in the training phase. This paper tackles this challenge by proposing a hierarchical mixture of directional statistical models. The model supports incrementally, continuously updating the activity model over time with the reduced annotation effort and without the need for storing historical sensor data. We have validated this solution on four publicly available, third-party smart home datasets, and have demonstrated up to 91.5 percent accuracies of detecting and recognising new activities.

Wireless sensor networks empowered with low-cost sensing devices and wireless communications present an opportunity to enable continuous, fine-grained data collection over a wide environment. However, the quality of data collected is susceptible to the hardware conditions and also adversarial external factors such as high variance in temperature and humidity. Over time, the sensors report erroneous readings, which deviate from true readings. To tackle the problem, we propose an efficient self-monitoring, self-managing and self-adaptive sensing framework based on a dynamic hybrid Bayesian network that combines Hidden Markov Model and Dynamic Linear Model. The framework does not only enable automatic on-line inference of true readings robustly but also monitor the working status of sensor nodes at the same time, which can uncover important insights on hardware management. The whole process also benefits from the derived approximation algorithm and thus supports on-line one-pass computation with minimum human intervention, which make the accurate formal inference affordable for distributed edge processing.

We have witnessed an increasing number of activity-aware applications being deployed in real-world environments, including smart home and mobile healthcare. The key enabler to these applications is sensor-based human activity recognition; that is, recognising and analysing human daily activities from wearable and ambient sensors. With the power of machine learning we can recognise complex correlations between various types of sensor data and the activities being observed. However the challenges still remain: (1) they often rely on a large amount of labelled training data to build the model, and (2) they cannot dynamically adapt the model with emerging or changing activity patterns over time. To directly address these challenges, we propose a Bayesian nonparametric model, i.e. Dirichlet process mixture of conditionally independent von Mises Fisher models, to enable both unsupervised and semi-supervised dynamic learning of human activities. The Bayesian nonparametric model can dynamically adapt itself to the evolving activity patterns without human intervention and the learning results can be used to alleviate the annotation effort. We evaluate our approach against real-world, third-party smart home datasets, and demonstrate significant improvements over the state-of-the-art techniques in both unsupervised and supervised settings.

Human activity recognition plays a significant role in enabling pervasive applications as it abstracts low-level noisy sensor data into high-level human activities, which applications can respond to. In this paper, we identify a new research question in activity recognition -- discovering and learning unknown activities that have not been pre-defined or observed. As pervasive systems intend to be deployed in a real-world environment for a long period of time, it is infeasible, to expect that users will only perform a set of pre-defined activities. Users might perform the same activities in a different manner, or perform a new type of activity. Failing to detect or update the activity model to incorporate new patterns or activities will outdate the model and result in unsatisfactory service delivery. To address this question, we explore the solution space and propose an estimation-based approach to not only discover and learn new activities over time, but also benefit from no need to store any historic sensor data.

Wireless sensor networks usually operate in dynamic, stochastic environments. While the behaviour of individual nodes is important, they are better seen as contributors to a larger mission, and managing the sensing quality and performance of these missions requires a range of online decisions to adapt to changing conditions. In this paper we propose an self-adaptive, self-managing and self-optimising sensing framework grounded in Bayesian dynamic linear models. Experimental results show that this solution can make sound scheduling decisions while also minimising energy usage.

Wireless Sensor Networks (WSNs) form a new paradigm of computing that allows the physical world to be measured at an unprecedented resolution; and the importance of the technology has been increasingly recognised. However, WSNs are still facing critical challenges, including low data quality and high energy consumption. In this thesis, formal statistical models are employed to address these two practical problems. With the formalism that is properly designed, sound statistical inferences can be made to guide local sensor nodes to make reasonable and timely decisions at local level in the face of uncertainties. To improve data reliability, we introduce formal Bayesian statistical method to form two on-line in-network fault detectors. The two detection techniques are well integrated with existing data collection protocols. Experimental results demonstrate the techniques have good detection accuracy but limited computational and communication overhead. To improve energy efficiency, we propose a novel data collection framework that features both energy conservation and data fault filtering by exploiting Hidden Markov Models (HMMs). Another data collection framework, a Dynamic Linear Model (DLM) based solution, featuring both adaptive sampling and efficient data collection is also proposed. Experimental results show the two solutions effectively suppress unnecessary packet transmission while satisfying users’ precision requirement. To prove the feasibility, we show all the proposed solutions are lightweight by either real world implementation or formal complexity analysis.