Deep Neural Networks (DNNs) have demonstrated remarkable success across various applications, yet some studies reveal their vulnerability to backdoor attacks, where attackers manipulate models under specific conditions using triggers. It significantly compromise the model integrity. Addressing this critical security issue requires robust defence mechanisms to ensure the reliability of DNN models. However, most existing defence mechanisms heavily rely on specialized defence datasets, which are often difficult to obtain due to data privacy and security concerns. This highlights the urgent need for effective data-free defence strategies. In this work, we propose Lipschitzness Precise Pruning (LPP), a novel data-free backdoor defence algorithm that leverages the properties of Lipschitz function to detect and mitigate backdoor vulnerabilities by pruning neurons with strong backdoor correlations while fine-tuning unaffected neurons. Our approach optimizes the computation of the Lipschitz constant using dot product properties, allowing for efficient and precise identification of compromised neurons without the need of clean defence data. This method addresses the limitations of existing data-free defences and extends the scope of backdoor mitigation to include fully connected layers, ensuring comprehensive protection of DNN models. As our approach does not require data exchange, it can be implemented efficiently and effectively in diverse environments. Extensive experiments demonstrate that LPP outperforms state-of-the-art defence approaches without the need for additional defence datasets. We release our code at: https://github.com/LMBTough/LPP

Recommendation systems have been essential for both user experience and platform efficiency by alleviating information overload and supporting decision-making. Traditional methods, i.e., content-based filtering, collaborative filtering, and deep learning, have achieved impressive results in recommendation systems. However, the cold-start and sparse-data scenarios are still challenging to deal with. Existing solutions either generate pseudo-interaction sequence, which often introduces redundant or noisy signals, or rely heavily on semantic similarity, overlooking dynamic shifts in user motivation. To address these limitations, this paper proposes a novel recommendation framework, termed M-LLM3REC, which leverages large language models for deep motivational signal extraction from limited user interactions. M-LLM3REC comprises three integrated modules: the Motivation-Oriented Profile Extractor (MOPE), Motivation-Oriented Trait Encoder (MOTE), and Motivational Alignment Recommender (MAR). By emphasizing motivation-driven semantic modeling, M-LLM3REC demonstrates robust, personalized, and generalizable recommendations, particularly boosting performance in cold-start situations in comparison with the state-of-the-art frameworks.

Recommender systems play a pivotal role in personalized content delivery but still face significant challenges in sparse interaction scenarios such as cold start conditions. Recent works have explored the integration of large language models (LLMs) into recommendation tasks. It has shown early promise but also reveals some limitations, such as hallucinations and overconfident outputs due to a lack of targeted modeling process. This paper introduces DAMA, a novel framework for Dual Alignment for Motivation-Aware recommendation. DAMA is the first framework to systematically incorporate LLM alignment into recommender system modeling. It employs a dual alignment mechanism that jointly optimizes semantic representations from two dimensions: user motivation modeling and product attribute modeling. By leveraging natural language feedback, DAMA facilitates a structured and interpretable alignment process. Extensive experimental results on multiple real-world datasets demonstrate that DAMA significantly improves recommendation performance, especially in cold start scenarios. We anticipate that DAMA will pioneer a new alignment-centric and semantically grounded paradigm for recommender systems.

Federated learning (FL) aims to train models collaboratively across clients without sharing data for privacy-preserving.However, one major challenge is the data heterogeneity issue, which refers to the biased labeling preferences at multiple clients.A number of existing FL methods attempt to tackle data heterogeneity locally (e.g., regularizing local models) or globally (e.g., fine-tuning global model), often neglecting inherent semantic information contained in each client.To explore the possibility of using intra-client semantically meaningful knowledge in handling data heterogeneity, in this paper, we propose Federated Learning with Semantic-Aware Collaboration (FedSC) to capture client-specific and class-relevant knowledge across heterogeneous clients.The core idea of FedSC is to construct relational prototypes and consistent prototypes at semantic-level, aiming to provide fruitful class underlying knowledge and stable convergence signals in a prototype-wise collaborative way.On the one hand, FedSC introduces an inter-contrastive learning strategy to bring instance-level embeddings closer to relational prototypes with the same semantics and away from distinct classes.On the other hand, FedSC devises consistent prototypes via a discrepancy aggregation manner, as a regularization penalty to constrain the optimization region of the local model.Moreover, a theoretical analysis for FedSC is provided to ensure a convergence guarantee.Experimental results on various challenging scenarios demonstrate the effectiveness of FedSC and the efficiency of crucial components.Our code is at https://github.com/hwang52/FedSC.

Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. To facilitate model safety, transfer-based attacks employ surrogate models to craft adversarial examples. In this work, we firstly study the intricate mechanisms of such attacks. We observe a correlation between the sharpness of decision boundaries in model sensitive regions and overfitting during adversarial training, which hampers the adversarial examples' transferability. To address this issue, we propose a novel approach termed Frequency-Guided Sample Relevance Attack (FGSRA). Specifically, we leverage frequency information to explore similar sensitive regions across different models, thereby generating neighborhood samples. Additional similarity weights are subsequently introduced to assess the adversarial contribution of the neighborhood samples. A hybrid gradient is then obtained to thoroughly exploit neighborhood information within input samples. Extensive experiments demonstrate the prominent performance of our approach. Compared to other state-of-the-art benchmarks on surrogate model Inc-v3, our method has an average improvement of 27.21% for normally trained CNNs and 42.1% for adversarially trained CNNs. Moreover, we achieve an average improvement of 24.6% for ViTs. Our code is available at:https://github.com/LMBTough/FGSRA

The way research and business manage and utilize knowledge is undergoing a significant transformation, driven by Artificial Intelligence (AI). Deep learning and machine learning are emerging as powerful tools for optimizing knowledge management systems, leading to more informed and productive development. AI offers unique solutions for organizations struggling with information overload and inefficient knowledge transfer. These AI models can significantly improve data management and utilization. Imagine an AI-powered system that streamlines onboarding processes, provides precise answers to various queries, and even captures the valuable tacit knowledge (implicit skills and expertise) often residing within individuals. AI bridges the gap between explicit knowledge (easily documented information) and tacit knowledge, fostering a more comprehensive and accessible knowledge base. However, such AI systems solicit trustworthy and responsible approaches to mitigate potential misuse and malfunction. In this workshop, we aim to gather researchers and engineers from academia and industry to discuss the latest advances in trustworthy and responsible AI solutions for information and knowledge management systems.

In knowledge distillation, a primary focus has been on transforming and balancing multiple distillation components. In this work, we emphasize the importance of thoroughly examining each distillation component, as we observe that not all elements are equally crucial. From this perspective, we decouple the Kullback-Leibler (KL) divergence into three unique elements: Binary Classification Divergence (BCD), Strong Correlation Divergence (SCD), and Weak Correlation Divergence (WCD). Each of these elements presents varying degrees of influence. Leveraging these insights, we present the Correlation-Aware Knowledge Distillation (CAKD) framework. CAKD is designed to prioritize the facets of the distillation components that have the most substantial influence on predictions, thereby optimizing knowledge transfer from teacher to student models. Our experiments demonstrate that adjusting the effect of each element enhances the effectiveness of knowledge transformation. Furthermore, evidence shows that our novel CAKD framework consistently outperforms the baseline across diverse models and datasets. Our work further highlights the importance and effectiveness of closely examining the impact of different parts of distillation process.

Adversarial generative models, such as Generative Adversarial Networks (GANs), are widely applied for generating various types of data, i.e., images, text, and audio. Accordingly, its promising performance has led to the GAN-based adversarial attack methods in the white-box and black-box attack scenarios. The importance of transferable black-box attacks lies in their ability to be effective across different models and settings, more closely aligning with real-world applications. However, it remains challenging to retain the performance in terms of transferable adversarial examples for such methods. Meanwhile, we observe that some enhanced gradient-based transferable adversarial attack algorithms require prolonged time for adversarial sample generation. Thus, in this work, we propose a novel algorithm named GE-AdvGAN to enhance the transferability of adversarial samples whilst improving the algorithm's efficiency. The main approach is via optimising the training process of the generator parameters. With the functional and characteristic similarity analysis, we introduce a novel gradient editing (GE) mechanism and verify its feasibility in generating transferable samples on various models. Moreover, by exploring the frequency domain information to determine the gradient editing direction, GE-AdvGAN can generate highly transferable adversarial samples while minimizing the execution time in comparison to the state-of-the-art transferable adversarial attack algorithms. The performance of GE-AdvGAN is comprehensively evaluated by large-scale experiments on different datasets, which results demonstrate the superiority of our algorithm. The code for our algorithm is available at: https://github.com/LMBTough/GE-advGAN.

The rapid development of deep learning has demonstrated its potential for deployment in many intelligent service systems. However, some issues such as optimisation (e.g., how to reduce the deployment resources costs and further improve the detection speed), especially in scenarios where limited resources are available, remain challenging to address. In this paper, we aim to delve into the principles of deep neural networks, focusing on the importance of network neurons. The goal is to identify the neurons that exert minimal impact on model performances, thereby aiding in the process of model pruning. In this work, we have thoroughly considered the deep learning model pruning process with and without fine-tuning step, ensuring the model performance consistency. To achieve our objectives, we propose a methodology that employs adversarial attack methods to explore deep neural network parameters. This approach is combined with an innovative attribution algorithm to analyse the level of network neurons involvement. In our experiments, our approach can effectively quantify the importance of network neuron. We extend the evaluation through comprehensive experiments conducted on a range of datasets, including CIFAR-10, CIFAR-100 and Caltech101. The results demonstrate that, our method have consistently achieved the state-of-the-art performance over many existing methods. We anticipate that this work will help to reduce the heavy training and inference cost of deep neural network models where a lightweight deep learning enhanced service and system is possible. The source code is open source at https://github.com/LMBTough/FVW.

Deep neural networks (DNNs) have been shown vulnerable to interference from adversarial samples, leading to erroneous predictions. Investigating adversarial attacks can effectively improve the reliability as well as the performance of deep neural models in real-world applications. Since it is generally challenging to infer the parameters in black-box models, high transferability becomes an important factor for the success rate of an attack method. Recently, the Spectrum Simulation Attack method exhibits promising results based on the frequency domain. In light of SSA, we propose a novel attack approach in this paper, which achieves the best results among diverse state-of-the-art transferable adversarial attack methods. Our method aims to find a stationary point, which extends the ability to find multiple local optima with the optimal local attack effect. After finding the stationary point, a frequency-based search is employed to explore the best adversarial samples in the neighbouring space, utilmately determining the final adversarial direction. We compare our method against a variety of cutting-edge transferable adversarial methods. Extensive experiments validate that our method improves the attack success rate by 4.7% for conventionally trained models and 53.1% for adversarially trained models. Our code is available at https://github.com/LMBTough/FSPS

Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite the vulnerable class, the non-vulnerable modules are difficult to be verified and determined as truly exploit free given the limited manual efforts available. It results in uncertainty, introduces labeling noise in the datasets and affects conclusion validity. To address this issue, we propose novel learning methods that are robust to label impurities and can leverage the most from limited label data; noisy label learning. We investigate various noisy label learning methods applied to software vulnerability prediction. Specifically, we propose a two-stage learning method based on noise cleaning to identify and remediate the noisy samples, which improves AUC and recall of baselines by up to 8.9% and 23.4%, respectively. Moreover, we discuss several hurdles in terms of achieving a performance upper bound with semi-omniscient knowledge of the label noise. Overall, the experimental results show that learning from noisy labels can be effective for data-driven software and security analytics.

Current machine-learning based software vulnerability detection methods are primarily conducted at the function-level. However, a key limitation of these methods is that they do not indicate the specific lines of code contributing to vulnerabilities. This limits the ability of developers to efficiently inspect and interpret the predictions from a learnt model, which is crucial for integrating machine-learning based tools into the software development work-flow. Graph-based models have shown promising performance in function-level vulnerability detection, but their capability for statement-level vulnerability detection has not been extensively explored. While interpreting function-level predictions through explainable AI is one promising direction, we herein consider the statement-level software vulnerability detection task from a fully supervised learning perspective. We propose a novel deep learning framework, LineVD, which formulates statement-level vulnerability detection as a node classification task. LineVD leverages control and data dependencies between statements using graph neural networks, and a transformer-based model to encode the raw source code tokens. In particular, by addressing the conflicting outputs between function-level and statement-level information, LineVD significantly improve the prediction performance without vulnerability status for function code. We have conducted extensive experiments against a large-scale collection of real-world C/C++ vulnerabilities obtained from multiple real-world projects, and demonstrate an increase of 105% in F1-score over the current state-of-the-art.

An intelligent industrial system is demanded for the development of Industry 4.0, which aims at providing efficient and intelligent computing service to increase the productivity. In-ternet of things become critical to achieve this goal by employing the sensors and connecting the objects over internet. In this study, we firstly investigate how the intelligent industrial service will be realised by constructing a five-layer framework based on our comprehensive field experiences. In detail, how the IoT sensor data are connected with the system and how the computational model is designed to improve the efficiency of the manufacturing system are discussed. Particularly, in this paper, the task of the defect identification of the steel is selected as our application on field. Since the longitudinal surface crack on the steel slab is a crucial indication suggesting the quality of continuous casting slab, how to discover the longitudinal surface crack on the slab in an early stage is of great significance. Traditional methods to detect the longitudinal surface crack have different drawbacks. Given the benefit of numerous IoT sensor data, we have proposed a novel computational model to incorporate the multiple factors of steel manufacturing system to improve the detection. Experiment evaluation has shown the efficiency and effectiveness of the model. In summary, we anticipate this work will contribute to an intelligent steel manufacturing system based on industrial IoT in building viable solutions, which benefit from the early stage identification and prediction of poor quality productions.

For classification tasks, such as protein-protein interactions (PPI), support vector machines (SVMs) have been continually utilised as a standard machine learning model. However, most practices in PPIs classifications are limited to common circumstances with small datasets and low feature dimensions, due to the big computation burden of kernel functions and quadratic optimization of SVM. Alternatively, these practical experiences might tend to employ a linear model once the dataset becomes larger, which may have exclusively lost the kernel function's potential. Since there are different defined kernels and various groups of hyperparameter, the time costs in estimating a best set of hyperparameter by traditional grid search are subsequently tremendous for PPI classification. To address this challenge, in this paper, we present a more efficient solution of hyperparameter estimation by gaining acceleration with GPU, which trains SVM efficiently and accurately with kernel functions calculation accelerated on various PPI datasets. The experiments are firstly conducted on PPI classification task, and we have exclusively evaluated the effectiveness on five public classification datasets. Our solution demonstrates a faster and more accurate performance comparing with the state-of-the-art.

Testable prediction outcomes generated by computational models based on available databases are the primary sources helping to design biological experiments. Although numerous databases have been designed by collecting data either only from literature manually or together with prediction outcomes from computational models, there is currently not a comprehensive data service framework delivering better insights for these results. In this paper, we introduce a biological sequence data service towards delivering deeper insights and helping better biological experiments design. The service includes following major components: a comprehensive database for storing biological data, data analytics tools for analysing biological data, and computational models for delivering testable prediction outcomes. Specifically, we present this service in a framework for studies on host-pathogen interactions. The design of this framework aims to improve the understanding of host-pathogen interactions. The relationships of hierarchical databases and their working mechanism, specifically between PPIs and DDIs, are also presented in this framework. Finally, the preliminary and practical experiences of building computational model for prediction is discussed.

Recent advances in the steel industry have encountered challenges in soliciting decision making solutions for quality control of products based on data mining techniques. In this paper, we present a steel quality control prediction system encompassing with real-world data as well as comprehensive data analysis results. The core process is cautiously designed as a regression problem, which is then best handled by grouping various learning algorithms with their massive resource of historical production datasets. The characteristics of the currently most popular learning models used in regression problem analysis are as well investigated and compared. The performance indicates our steel quality control prediction system based on ensemble machine learning model can offer promising result whilst delivering high usability for local manufacturers to address the production problem by aid of development of machine learning techniques. Furthermore, real-world deployment of this system is demonstrated and discussed. Finally, future directions and the performance expectation are pointed out.