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.

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.

Advances in machine learning have enabled a broad range of complex applications, such as image recognition, recommendation system and machine translation. Data plays an important role in our increasingly complex and diverse environments, and this also reinforces the importance of data privacy in machine learning-enabled applications. Although there are a number of literature survey articles on machine learning, only a few studies have investigated the cryptographic primitives used in privacy-preserving machine learning (PPML). In other words, there is no, or limited, systematization of knowledge (SoK) that provides a comprehensive introduction to cryptography that have been deployed in PPML. In this paper, we firstly introduce some basic concepts such as machine learning tasks and processes. Then, we review and systematize the cryptographic primitives used in PPML. We analyze these existing privacy-preserving schemes in their learning process, especially training and inference. Finally, we conclude our survey and provide an outlook on future trends and research directions in the field.

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

To ensure the security of outsourced data without affecting data availability, one can use Symmetric Searchable Encryption (SSE) to achieve search over encrypted data. Considering that query users may search with misspelled words, the fuzzy search should be supported. However, conventional privacy-preserving fuzzy multi-keyword search schemes are incapable of achieving the result verification and adaptive security. To solve the above challenging issues, in this paper we propose a Verifiable Fuzzy multi-keyword Search scheme with Adaptive security (VFSA). VFSA first employs the locality sensitive hashing to hash the misspelled and correct keywords to the same positions, then designs a twin Bloom filter for each document to store and mask all keywords contained in the document, next constructs an index tree based on the graph-based keyword partition algorithm to achieve adaptive sublinear retrieval, finally combines the Merkle hash tree structure with the adapted multiset accumulator to check the correctness and completeness of search results. Our formal security analysis shows that VFSA is secure under the IND-CKA2 model and achieves query authentication. Our empirical experiments using the real-world dataset demonstrate the practicality of VFSA.

Supporting efficient and secure location-based skyline queries on encrypted data, such as private data outsourced to cloud-based systems, remains an ongoing challenge for efficiency due to significant computational costs in the ciphertext domain. To accelerate privacy-preserving skyline queries, the secure index intuitively contributes to an increase in efficiency. However, designing such a secure index is a challenge while protecting the unlinkability of queries. Meanwhile, there exist little work that can commendably assure efficiency and security. In this paper, we demonstrate SecSky, an efficient solution for supporting secure location-based skyline queries through the secure index. To support SecSky, we devise a novel unified structure, named secure R-tree (SR-tree) index, without privacy leakage (especially indirect privacy). Subsequently, we propose a novel secure location-based dominance protocol, which is utilized to calculate the dominance relationship on the SR-tree. Using this protocol as the building block, our secure location-based skyline query protocol integrates SR-tree, permutation and perturbation techniques to facilitate query processing so as to dramatically reduce the computational overhead. Meanwhile, our proposed solution avoids compromising the privacy of datasets, queries, dominance relationship and skyline results. Finally, we analyze the complexity and security of SecSky. Findings from the experimental evaluation show that our proposed scheme outperforms several other protocols by at least 3 orders of magnitude in terms of query efficiency.

Thanks to rapid advancements in microprocessors, battery technologies, and lightweight materials, unmanned aerial vehicles (UAVs), commonly known as drones, have received signif-icant interest in the past few years. As drone-related commercial and civilian applications are flourishing, Internet-of-Drones (IoD) is moving into the fast lane and quickly becoming a highly anticipated network paradigm, where drones and Zone Service Providers (ZSPs) coordinate knowledge sharing in a reliable, accurate, and efficient way. However, for the sake of both strategic and financial value to business and mission critical applications, it is of vital importance to address both data security and privacy preservation issues brought by drones' inherent resource constraints and wide-open wireless medium. In this paper, we propose a secure data collection and storage mechanism, also called SecureIoD, for the IoD environment. In SecureIoD, drones and ZSPs first mutually authenticate each other and establish a secure session key before sharing any sensitive data via an insecure wireless channel. Then, ZSPs pack the collected data into blocks and compete to add their blocks into the blockchain. We also propose a joint Proof-of- Work (PoW) and Proof-of-Stake (PoS) consensus mechanism to select the miner ZSP, where the more transactions are in the block, the easier a ZSP can solve the cryptographic puzzle. We present security verification and analysis to show that SecureIoD can resist various security attacks. Finally, we develop a real-world testbed, implement SecureIoD and existing SDDM and BACSIoD schemes, and carry out extensive simulation experiments for performance evaluation and analysis. Experimental results reveal that not only does SecureIoD have lower computation cost, energy consumption, miner selection time, and communication overhead, but also offer better security features and capabilities.

Blockchain has transitioned beyond the hype to reality, as evidenced by the amount of research it has attracted and by its commercial applications. One popular application of blockchain is in cybersecurity, which is the focus of this paper. Specifically, we performed a systematic literature review of blockchain use cases for cybersecurity, while focusing on articles published over the past decade. Based on our analysis of 111 articles, we developed a classification framework using the thematic analysis approach. This classification framework is designed to offer readers a comprehensive perspective of the potential of blockchain to enhance cybersecurity in different contexts. The findings have implications for research and practice.

Deep learning is increasingly popular, partly due to its widespread application potential, such as in civilian, government and military domains. Given the exacting computational requirements, cloud computing has been utilized to host user data and model. However, such an approach has potential privacy implications. Therefore, in this paper, we propose a method to protect user’s privacy in the inference phase of deep learning workflow. Specifically, we use an intermediate layer to separate the entire neural network into two parts, which are respectively deployed on the user device and the cloud server. Theencoder, deployed on the user device, is used for raw data transformation, which removes the need for users to upload raw data to the cloud directly. However, we also demonstrate there exists potential for privacy leakage in the intermediate features of the neural network through two concrete experiments. In other words, the encoder on its own does not provide adequate privacy protection. Therefore, we also propose an approach to achievePrivacy-preserving Feature Extraction based on Adversarial Training (P-FEAT), where the goal of privacy attacking tasks and the goal of target tasks are adversarial in terms of sensitive attributes. By imposing privacy constraints during the feature extraction, we can reduce the contribution of the extracted features to the privacy leakage. In this way, privacy protection capability of theencodercan be further strengthened. We then demonstrate the effectiveness of P-FEAT using a large number of experiments, whose findings show that P-FEAT can significantly reduce the threats of privacy attacking tasks while maintaining high accuracy of the target tasks.

Homomorphic encryption (HE) schemes, such as fully homomorphic encryption (FHE), support a number of useful computations on ciphertext in a broad range of applications, such as e-voting, private information retrieval, cloud security, and privacy protection. While FHE schemes do not require any interaction during computation, the key limitations are large ciphertext expansion and inefficiency. Thus, to overcome these limitations, we develop a novel cryptographic tool, MAS-Encryption (MASE), to support real-value input and secure computation on the multiply-add structure. The multiply-add structures exist in many important protocols, such as classifiers and outsourced protocols, and we will explain how MASE can be used to protect the privacy of these protocols, using two case study examples. Specifically, the first case study example is the privacy-preserving Naive Bayes classifier that can achieve minimal Bayes risk, and the other example is the privacy-preserving support vector machine. We prove that the constructed classifiers are secure and evaluate their performance using real-world datasets. Experiments show that our proposed MASE scheme and MASE based classifiers are efficient, in the sense that we achieve an optimal tradeoff between computation efficiency and communication interactions. Thus, we avoid the inefficiency of FHE based paradigm.

While being a lasting theme, privacy, security, and trust (PST) has been increasingly important in recent days due to the pervasive (but more prone) computation infrastructure and deep (but more intrusive) data analytics, and has been hugely demanded from governments, companies, and individuals. This workshop aims at providing a forum for researchers, practitioners and developers from different background areas such as computational intelligence, data privacy and cyber security, trust management, cloud computing, edge computing, Internet of Things, big data analytics, machine learning and data mining, knowledge discovery to exchange the latest experience, research ideas and synergic research and development on fundamental issues and applications about privacy, security and trust issues in computational intelligence.

Dynamic Searchable Symmetric Encryption (DSSE) has gained increasing popularity as it enables users to perform both file updates and ciphertext retrieval over encrypted data . However, existing DSSE schemes still lead to privacy leakage ( e.g., forward and backward privacy) in the dynamic setting. Some forward and backward secure DSSE schemes have been proposed, but still cannot support the keyword shielding flexibly. To solve this challenging issue, we propose a Forward and Backward Authorized Keyword Search (FB-AKS) scheme with recoverable keyword shielding by using trapdoor permutations and puncturable encryption in this paper. Compared with existing forward and backward private schemes, FB-AKS achieves keyword authorization flexibly ( e.g., keyword shielding, keyword un-shielding). The formal security analysis proves that FB-AKS achieves forward and backward security. And extensive experiments demonstrate that FB-AKS has less computation and storage overheads .

The need to efficiently store and query large scale graph datasets is evident in the growing number of data-intensive applications, particularly to maximize the mining of intelligence from these data (e.g., to inform decision making). However, directly releasing graph dataset for analysis may leak sensitive information of an individual even if the graph is anonymized, as demonstrated by the re-identification attacks on the DBpedia datasets. A key challenge in the design of graph sanitization methods is scalability, as existing execution models generally have significant memory requirements. In this paper, we propose a novel k-decomposition algorithm and define a new information loss matrix designed for utility measurement in massively large graph datasets. We also propose a novel privacy preserving framework that can be seamlessly integrated with graph storage, anonymization, query processing, and analysis. Our experimental studies show that the proposed solution achieves privacy-preserving, utility, and efficiency.

Leisure travelers most often travel in groups with family, relatives or friends. It is argued that tourist information search tends to be more collaborative than a completely individual decision-making exercise. Collaborative information seeking (CIS) deals with collaboration in searching for information. In recent years, social media has been steadily increasing as an important information source for tourists who access social media frequently through their mobile devices. Research has shown that travelers rely more on the suggestions and reviews provided by experienced tourists for their travel planning and decision-making. Tourists undertake social search during which they exploit their social networks/relationships to improve the search process. However, limited research has investigated social media users' behaviors in collaborative search for tourism information. What is the role of social media in supporting of collaborative tourism information search, including collaborative search patterns and strategies in social environments, has remained unknown. This research aims to investigate mobile social media users' behaviors in collaborative search for tourism information. Using the Grounded Theory approach, a conceptual framework of mobile social media users' tourism CIS behavior will be built. Semi-structured in-depth interviews will be employed to collect users' search experiences.