Search

AI Safety is an emerging area of critical importance to the safe adoption and deployment of AI systems. With the rapid proliferation of AI and especially with the recent advancement of Generative AI (or GAI), the technology ecosystem behind the design, development, adoption, and deployment of AI systems has drastically changed, broadening the scope of AI Safety to address impacts on public safety and national security. In this paper, we propose a novel architectural framework for understanding and analyzing AI Safety; defining its characteristics from three perspectives: Trustworthy AI, Responsible AI, and Safe AI. We provide an extensive review of current research and advancements in AI safety from these perspectives, highlighting their key challenges and mitigation approaches. Through examples from state-of-the-art technologies, particularly Large Language Models (LLMs), we present innovative mechanism, methodologies, and techniques for designing and testing AI safety. Our goal is to promote advancement in AI safety research, and ultimately enhance people's trust in digital transformation.

Skeleton Action Recognition (SAR) has attracted significant interest for its efficient representation of the human skeletal structure. Despite its advancements, recent studies have raised security concerns in SAR models, particularly their vulnerability to adversarial attacks. However, such strategies are limited to digital scenarios and ineffective in physical attacks, limiting their real-world applicability. To investigate the vulnerabilities of SAR in the physical world, we introduce the Physical Skeleton Backdoor Attacks (PSBA), the first exploration of physical backdoor attacks against SAR. Considering the practicalities of physical execution, we introduce a novel trigger implantation method that integrates infrequent and imperceivable actions as triggers into the original skeleton data. By incorporating a minimal amount of this manipulated data into the training set, PSBA enables the system misclassify any skeleton sequences into the target class when the trigger action is present. We examine the resilience of PSBA in both poisoned and clean-label scenarios, demonstrating its efficacy across a range of datasets, poisoning ratios, and model architectures. Additionally, we introduce a trigger-enhancing strategy to strengthen attack performance in the clean label setting. The robustness of PSBA is tested against three distinct backdoor defenses, and the stealthiness of PSBA is evaluated using two quantitative metrics. Furthermore, by employing a Kinect V2 camera, we compile a dataset of human actions from the real world to mimic physical attack situations, with our findings confirming the effectiveness of our proposed attacks. Our project website can be found at https://qichenzheng.github.io/psba-website., Comment: Accepted by ECCV 2024

Deep neural networks are proven to be vulnerable to data poisoning attacks. Recently, a specific type of data poisoning attack known as availability attacks has led to the failure of data utilization for model learning by adding imperceptible perturbations to images. Consequently, it is quite beneficial and challenging to detect poisoned samples, also known as Unlearnable Examples (UEs), from a mixed dataset. In response, we propose an Iterative Filtering approach for UEs identification. This method leverages the distinction between the inherent semantic mapping rules and shortcuts, without the need for any additional information. We verify that when training a classifier on a mixed dataset containing both UEs and clean data, the model tends to quickly adapt to the UEs compared to the clean data. Due to the accuracy gaps between training with clean/poisoned samples, we employ a model to misclassify clean samples while correctly identifying the poisoned ones. The incorporation of additional classes and iterative refinement enhances the model's ability to differentiate between clean and poisoned samples. Extensive experiments demonstrate the superiority of our method over state-of-the-art detection approaches across various attacks, datasets, and poison ratios, significantly reducing the Half Total Error Rate (HTER) compared to existing methods., Comment: Accepted by ICANN 2024

Emerging Internet of Things (IoT) platforms provide sophisticated capabilities to automate IoT services by enabling occupants to create trigger-action rules. Multiple trigger-action rules can physically interact with each other via shared environment channels, such as temperature, humidity, and illumination. We refer to inter-rule interactions via shared environment channels as a physical inter-rule vulnerability. Such vulnerability can be exploited by attackers to launch attacks against IoT systems. We propose a new framework to proactively discover possible physical inter-rule interactions from user requirement specifications (i.e., descriptions) using a deep learning approach. Specifically, we utilize the Transformer model to generate trigger-action rules from their associated descriptions. We discover two types of physical inter-rule vulnerabilities and determine associated environment channels using natural language processing (NLP) tools. Given the extracted trigger-action rules and associated environment channels, an approach is proposed to identify hidden physical inter-rule vulnerabilities among them. Our experiment on 27983 IFTTT style rules shows that the Transformer can successfully extract trigger-action rules from descriptions with 95.22% accuracy. We also validate the effectiveness of our approach on 60 SmartThings official IoT apps and discover 99 possible physical inter-rule vulnerabilities., Comment: Accepted by IEEE ICWS 2024 Workshop

Federated Unlearning (FU) is gaining prominence for its capability to eliminate influences of Federated Learning (FL) users' data from trained global FL models. A straightforward FU method involves removing the unlearned users and subsequently retraining a new global FL model from scratch with all remaining users, a process that leads to considerable overhead. To enhance unlearning efficiency, a widely adopted strategy employs clustering, dividing FL users into clusters, with each cluster maintaining its own FL model. The final inference is then determined by aggregating the majority vote from the inferences of these sub-models. This method confines unlearning processes to individual clusters for removing a user, thereby enhancing unlearning efficiency by eliminating the need for participation from all remaining users. However, current clustering-based FU schemes mainly concentrate on refining clustering to boost unlearning efficiency but overlook the potential information leakage from FL users' gradients, a privacy concern that has been extensively studied. Typically, integrating secure aggregation (SecAgg) schemes within each cluster can facilitate a privacy-preserving FU. Nevertheless, crafting a clustering methodology that seamlessly incorporates SecAgg schemes is challenging, particularly in scenarios involving adversarial users and dynamic users. In this connection, we systematically explore the integration of SecAgg protocols within the most widely used federated unlearning scheme, which is based on clustering, to establish a privacy-preserving FU framework, aimed at ensuring privacy while effectively managing dynamic user participation. Comprehensive theoretical assessments and experimental results show that our proposed scheme achieves comparable unlearning effectiveness, alongside offering improved privacy protection and resilience in the face of varying user participation.

In recent years, Federated Unlearning (FU) has gained attention for addressing the removal of a client's influence from the global model in Federated Learning (FL) systems, thereby ensuring the ``right to be forgotten" (RTBF). State-of-the-art methods for unlearning use historical data from FL clients, such as gradients or locally trained models. However, studies have revealed significant information leakage in this setting, with the possibility of reconstructing a user's local data from their uploaded information. Addressing this, we propose Starfish, a privacy-preserving federated unlearning scheme using Two-Party Computation (2PC) techniques and shared historical client data between two non-colluding servers. Starfish builds upon existing FU methods to ensure privacy in unlearning processes. To enhance the efficiency of privacy-preserving FU evaluations, we suggest 2PC-friendly alternatives for certain FU algorithm operations. We also implement strategies to reduce costs associated with 2PC operations and lessen cumulative approximation errors. Moreover, we establish a theoretical bound for the difference between the unlearned global model via Starfish and a global model retrained from scratch for certified client removal. Our theoretical and experimental analyses demonstrate that Starfish achieves effective unlearning with reasonable efficiency, maintaining privacy and security in FL systems.

Low earth orbit (LEO) satellite systems play an important role in next generation communication networks due to their ability to provide extensive global coverage with guaranteed communications in remote areas and isolated areas where base stations cannot be cost-efficiently deployed. With the pervasive adoption of LEO satellite systems, especially in the LEO Internet-of-Things (IoT) scenarios, their spectrum resource management requirements have become more complex as a result of massive service requests and high bandwidth demand from terrestrial terminals. For instance, when leasing the spectrum to terrestrial users and controlling the uplink transmit power, satellites collect user data for machine learning purposes, which usually are sensitive information such as location, budget and quality of service (QoS) requirement. To facilitate model training in LEO IoT while preserving the privacy of data, blockchain-driven federated learning (FL) is widely used by leveraging on a fully decentralized architecture. In this paper, we propose a hybrid spectrum pricing and power control framework for LEO IoT by combining blockchain technology and FL. We first design a local deep reinforcement learning algorithm for LEO satellite systems to learn a revenue-maximizing pricing and power control scheme. Then the agents collaborate to form a FL system. We also propose a reputation-based blockchain which is used in the global model aggregation phase of FL. Based on the reputation mechanism, a node is selected for each global training round to perform model aggregation and block generation, which can further enhance the decentralization of the network and guarantee the trust. Simulation tests are conducted to evaluate the performances of the proposed scheme. Our results show the efficiency of finding the maximum revenue scheme for LEO satellite systems while preserving the privacy of each agent.

In copy-move tampering operations, perpetrators often employ techniques, such as blurring, to conceal tampering traces, posing significant challenges to the detection of object-level targets with intact structures. Focus on these challenges, this paper proposes an Object-level Copy-Move Forgery Image Detection based on Inconsistency Mining (IMNet). To obtain complete object-level targets, we customize prototypes for both the source and tampered regions and dynamically update them. Additionally, we extract inconsistent regions between coarse similar regions obtained through self-correlation calculations and regions composed of prototypes. The detected inconsistent regions are used as supplements to coarse similar regions to refine pixel-level detection. We operate experiments on three public datasets which validate the effectiveness and the robustness of the proposed IMNet., Comment: 4 pages, 2 figures, Accepted to WWW 2024

Many attack techniques have been proposed to explore the vulnerability of DNNs and further help to improve their robustness. Despite the significant progress made recently, existing black-box attack methods still suffer from unsatisfactory performance due to the vast number of queries needed to optimize desired perturbations. Besides, the other critical challenge is that adversarial examples built in a noise-adding manner are abnormal and struggle to successfully attack robust models, whose robustness is enhanced by adversarial training against small perturbations. There is no doubt that these two issues mentioned above will significantly increase the risk of exposure and result in a failure to dig deeply into the vulnerability of DNNs. Hence, it is necessary to evaluate DNNs' fragility sufficiently under query-limited settings in a non-additional way. In this paper, we propose the Spatial Transform Black-box Attack (STBA), a novel framework to craft formidable adversarial examples in the query-limited scenario. Specifically, STBA introduces a flow field to the high-frequency part of clean images to generate adversarial examples and adopts the following two processes to enhance their naturalness and significantly improve the query efficiency: a) we apply an estimated flow field to the high-frequency part of clean images to generate adversarial examples instead of introducing external noise to the benign image, and b) we leverage an efficient gradient estimation method based on a batch of samples to optimize such an ideal flow field under query-limited settings. Compared to existing score-based black-box baselines, extensive experiments indicated that STBA could effectively improve the imperceptibility of the adversarial examples and remarkably boost the attack success rate under query-limited settings.

The Internet of Vehicles (IoV) has great potential to transform transportation systems by enhancing road safety, reducing traffic congestion, and improving user experience through onboard infotainment applications. Decentralized data sharing can improve security, privacy, reliability, and facilitate infotainment data sharing in IoVs. However, decentralized data sharing may not achieve the expected efficiency if there are IoV users who only want to consume the shared data but are not willing to contribute their own data to the community, resulting in incomplete information observed by other vehicles and infrastructure, which can introduce additional transmission latency. Therefore, in this article, by modeling the data sharing ecosystem as a data trading market, we propose a decentralized data-sharing incentive mechanism based on multi-intelligent reinforcement learning to learn the supply-demand balance in markets and minimize transmission latency. Our proposed mechanism takes into account the dynamic nature of IoV markets, which can experience frequent fluctuations in supply and demand. We propose a time-sensitive Key-Policy Attribute-Based Encryption (KP-ABE) mechanism coupled with Named Data Networking (NDN) to protect data in IoVs, which adds a layer of security to our proposed solution. Additionally, we design a decentralized market for efficient data sharing in IoVs, where continuous double auctions are adopted. The proposed mechanism based on multi-agent deep reinforcement learning can learn the supply-demand equilibrium in markets, thus improving the efficiency and sustainability of markets. Theoretical analysis and experimental results show that our proposed learning-based incentive mechanism outperforms baselines by 10% in determining the equilibrium of supply and demand while reducing transmission latency by 20%.

Artificial Intelligence-Generated Content (AIGC) refers to the paradigm of automated content generation utilizing AI models. Mobile AIGC services in the Internet of Vehicles (IoV) network have numerous advantages over traditional cloud-based AIGC services, including enhanced network efficiency, better reconfigurability, and stronger data security and privacy. Nonetheless, AIGC service provisioning frequently demands significant resources. Consequently, resource-constrained roadside units (RSUs) face challenges in maintaining a heterogeneous pool of AIGC services and addressing all user service requests without degrading overall performance. Therefore, in this paper, we propose a decentralized incentive mechanism for mobile AIGC service allocation, employing multi-agent deep reinforcement learning to find the balance between the supply of AIGC services on RSUs and user demand for services within the IoV context, optimizing user experience and minimizing transmission latency. Experimental results demonstrate that our approach achieves superior performance compared to other baseline models., Comment: 2023 IEEE 98th Vehicular Technology Conference (VTC2023-Fall)

This paper aims to provide differentiated security protection for infotainment data communication in Internet-of-Vehicle (IoV) networks. The IoV is a network of vehicles that uses various sensors, software, built-in hardware, and communication technologies to enable information exchange between pedestrians, cars, and urban infrastructure. Negligence on the security of infotainment data communication in IoV networks can unintentionally open an easy access point for social engineering attacks. The attacker can spread false information about traffic conditions, mislead drivers in their directions, and interfere with traffic management. Such attacks can also cause distractions to the driver, which has a potential implication for the safety of driving. The existing literature on IoV communication and network security focuses mainly on generic solutions. In a heterogeneous communication network where different types of communication coexist, we can improve the efficiency of security solutions by considering the different security and efficiency requirements of data communications. Hence, we propose a differentiated security mechanism for protecting infotainment data communication in IoV networks. In particular, we first classify data communication in the IoV network, examine the security focus of each data communication, and then develop a differentiated security architecture to provide security protection on a file-to-file basis. Our architecture leverages Named Data Networking (NDN) so that infotainment files can be efficiently circulated throughout the network where any node can own a copy of the file, thus improving the hit ratio for user file requests. In addition, we propose a time-sensitive Key-Policy Attribute-Based Encryption (KP-ABE) scheme for sharing subscription-based infotainment data..., Comment: 16th International Conference on Network and System Security

Machine Unlearning (MU) has gained considerable attention recently for its potential to achieve Safe AI by removing the influence of specific data from trained machine learning models. This process, known as knowledge removal, addresses AI governance concerns of training data such as quality, sensitivity, copyright restrictions, and obsolescence. This capability is also crucial for ensuring compliance with privacy regulations such as the Right To Be Forgotten. Furthermore, effective knowledge removal mitigates the risk of harmful outcomes, safeguarding against biases, misinformation, and unauthorized data exploitation, thereby enhancing the safe and responsible use of AI systems. Efforts have been made to design efficient unlearning approaches, with MU services being examined for integration with existing machine learning as a service, allowing users to submit requests to remove specific data from the training corpus. However, recent research highlights vulnerabilities in machine unlearning systems, such as information leakage and malicious unlearning requests, that can lead to significant security and privacy concerns. Moreover, extensive research indicates that unlearning methods and prevalent attacks fulfill diverse roles within MU systems. For instance, unlearning can act as a mechanism to recover models from backdoor attacks, while backdoor attacks themselves can serve as an evaluation metric for unlearning effectiveness. This underscores the intricate relationship and complex interplay among these mechanisms in maintaining system functionality and safety. This survey aims to fill the gap between the extensive number of studies on threats, attacks, and defenses in machine unlearning and the absence of a comprehensive review that categorizes their taxonomy, methods, and solutions, thus offering valuable insights for future research directions and practical implementations.

Federated Learning (FL) is a promising machine learning approach for Internet of Things (IoT), but it has to address network congestion problems when the population of IoT devices grows. Hierarchical FL (HFL) alleviates this issue by distributing model aggregation to multiple edge servers. Nevertheless, the challenge of communication overhead remains, especially in scenarios where all IoT devices simultaneously join the training process. For scalability, practical HFL schemes select a subset of IoT devices to participate in the training, hence the notion of device scheduling. In this setting, only selected IoT devices are scheduled to participate in the global training, with each of them being assigned to one edge server. Existing HFL assignment methods are primarily based on search mechanisms, which suffer from high latency in finding the optimal assignment. This paper proposes an improved K-Center algorithm for device scheduling and introduces a deep reinforcement learning-based approach for assigning IoT devices to edge servers. Experiments show that scheduling 50% of IoT devices is generally adequate for achieving convergence in HFL with much lower time delay and energy consumption. In cases where reduction in energy consumption (such as in Green AI) and reduction of messages (to avoid burst traffic) are key objectives, scheduling 30% IoT devices allows a substantial reduction in energy and messages with similar model accuracy., Comment: Published in IEEE Internet of Things Journal (IoT-J)

With the rapid development of low-cost consumer electronics and cloud computing, Internet-of-Things (IoT) devices are widely adopted for supporting next-generation distributed systems such as smart cities and industrial control systems. IoT devices are often susceptible to cyber attacks due to their open deployment environment and limited computing capabilities for stringent security controls. Hence, Intrusion Detection Systems (IDS) have emerged as one of the effective ways of securing IoT networks by monitoring and detecting abnormal activities. However, existing IDS approaches rely on centralized servers to generate behaviour profiles and detect anomalies, causing high response time and large operational costs due to communication overhead. Besides, sharing of behaviour data in an open and distributed IoT network environment may violate on-device privacy requirements. Additionally, various IoT devices tend to capture heterogeneous data, which complicates the training of behaviour models. In this paper, we introduce Federated Learning (FL) to collaboratively train a decentralized shared model of IDS, without exposing training data to others. Furthermore, we propose an effective method called Federated Learning Ensemble Knowledge Distillation (FLEKD) to mitigate the heterogeneity problems across various clients. FLEKD enables a more flexible aggregation method than conventional model fusion techniques. Experiment results on the public dataset CICIDS2019 demonstrate that the proposed approach outperforms local training and traditional FL in terms of both speed and performance and significantly improves the system's ability to detect unknown attacks. Finally, we evaluate our proposed framework's performance in three potential real-world scenarios and show FLEKD has a clear advantage in experimental results.

Federated learning (FL) is vulnerable to poisoning attacks, where malicious clients manipulate their updates to affect the global model. Although various methods exist for detecting those clients in FL, identifying malicious clients requires sufficient model updates, and hence by the time malicious clients are detected, FL models have been already poisoned. Thus, a method is needed to recover an accurate global model after malicious clients are identified. Current recovery methods rely on (i) all historical information from participating FL clients and (ii) the initial model unaffected by the malicious clients, leading to a high demand for storage and computational resources. In this paper, we show that highly effective recovery can still be achieved based on (i) selective historical information rather than all historical information and (ii) a historical model that has not been significantly affected by malicious clients rather than the initial model. In this scenario, while maintaining comparable recovery performance, we can accelerate the recovery speed and decrease memory consumption. Following this concept, we introduce Crab, an efficient and certified recovery method, which relies on selective information storage and adaptive model rollback. Theoretically, we demonstrate that the difference between the global model recovered by Crab and the one recovered by train-from-scratch can be bounded under certain assumptions. Our empirical evaluation, conducted across three datasets over multiple machine learning models, and a variety of untargeted and targeted poisoning attacks reveals that Crab is both accurate and efficient, and consistently outperforms previous approaches in terms of both recovery speed and memory consumption.

Extensive studies have demonstrated that deep neural networks (DNNs) are vulnerable to adversarial attacks, which brings a huge security risk to the further application of DNNs, especially for the AI models developed in the real world. Despite the significant progress that has been made recently, existing attack methods still suffer from the unsatisfactory performance of escaping from being detected by naked human eyes due to the formulation of adversarial example (AE) heavily relying on a noise-adding manner. Such mentioned challenges will significantly increase the risk of exposure and result in an attack to be failed. Therefore, in this paper, we propose the Salient Spatially Transformed Attack (SSTA), a novel framework to craft imperceptible AEs, which enhance the stealthiness of AEs by estimating a smooth spatial transform metric on a most critical area to generate AEs instead of adding external noise to the whole image. Compared to state-of-the-art baselines, extensive experiments indicated that SSTA could effectively improve the imperceptibility of the AEs while maintaining a 100\% attack success rate.

In recent years, the notion of ``the right to be forgotten" (RTBF) has become a crucial aspect of data privacy for digital trust and AI safety, requiring the provision of mechanisms that support the removal of personal data of individuals upon their requests. Consequently, machine unlearning (MU) has gained considerable attention which allows an ML model to selectively eliminate identifiable information. Evolving from MU, federated unlearning (FU) has emerged to confront the challenge of data erasure within federated learning (FL) settings, which empowers the FL model to unlearn an FL client or identifiable information pertaining to the client. Nevertheless, the distinctive attributes of federated learning introduce specific challenges for FU techniques. These challenges necessitate a tailored design when developing FU algorithms. While various concepts and numerous federated unlearning schemes exist in this field, the unified workflow and tailored design of FU are not yet well understood. Therefore, this comprehensive survey delves into the techniques and methodologies in FU providing an overview of fundamental concepts and principles, evaluating existing federated unlearning algorithms, and reviewing optimizations tailored to federated learning. Additionally, it discusses practical applications and assesses their limitations. Finally, it outlines promising directions for future research., Comment: Accepted by ACM Computing Surveys

The emergence of foundation models, including language and vision models, has reshaped AI's landscape, offering capabilities across various applications. Deploying and fine-tuning these large models, like GPT-3 and BERT, presents challenges, especially in the current foundation model era. We introduce Emulator-Assisted Tuning (EAT) combined with Parameter-Efficient Fine-Tuning (PEFT) to form Parameter-Efficient Emulator-Assisted Tuning (PEAT). Further, we expand this into federated learning as Federated PEAT (FedPEAT). FedPEAT uses adapters, emulators, and PEFT for federated model tuning, enhancing model privacy and memory efficiency. Adapters adjust pre-trained models, while emulators give a compact representation of original models, addressing both privacy and efficiency. Adaptable to various neural networks, our approach also uses deep reinforcement learning for hyper-parameter optimization. We tested FedPEAT in a unique scenario with a server participating in collaborative federated tuning, showcasing its potential in tackling foundation model challenges.

Training a large and state-of-the-art machine learning model typically necessitates the use of large-scale datasets, which, in turn, makes the training and parameter-tuning process expensive and time-consuming. Some researchers opt to distil information from real-world datasets into tiny and compact synthetic datasets while maintaining their ability to train a well-performing model, hence proposing a data-efficient method known as Dataset Distillation (DD). Despite recent progress in this field, existing methods still underperform and cannot effectively replace large datasets. In this paper, unlike previous methods that focus solely on improving the efficacy of student distillation, we are the first to recognize the important interplay between expert and student. We argue the significant impact of expert smoothness when employing more potent expert trajectories in subsequent dataset distillation. Based on this, we introduce the integration of clipping loss and gradient penalty to regulate the rate of parameter changes in expert trajectories. Furthermore, in response to the sensitivity exhibited towards randomly initialized variables during distillation, we propose representative initialization for synthetic dataset and balanced inner-loop loss. Finally, we present two enhancement strategies, namely intermediate matching loss and weight perturbation, to mitigate the potential occurrence of cumulative errors. We conduct extensive experiments on datasets of different scales, sizes, and resolutions. The results demonstrate that the proposed method significantly outperforms prior methods.

Previous studies have revealed that artificial intelligence (AI) systems are vulnerable to adversarial attacks. Among them, model extraction attacks fool the target model by generating adversarial examples on a substitute model. The core of such an attack is training a substitute model as similar to the target model as possible, where the simulation process can be categorized in a data-dependent and data-free manner. Compared with the data-dependent method, the data-free one has been proven to be more practical in the real world since it trains the substitute model with synthesized data. However, the distribution of these fake data lacks diversity and cannot detect the decision boundary of the target model well, resulting in the dissatisfactory simulation effect. Besides, these data-free techniques need a vast number of queries to train the substitute model, increasing the time and computing consumption and the risk of exposure. To solve the aforementioned problems, in this paper, we propose a novel data-free model extraction method named SCME (Self-Contrastive Model Extraction), which considers both the inter- and intra-class diversity in synthesizing fake data. In addition, SCME introduces the Mixup operation to augment the fake data, which can explore the target model's decision boundary effectively and improve the simulating capacity. Extensive experiments show that the proposed method can yield diversified fake data. Moreover, our method has shown superiority in many different attack settings under the query-limited scenario, especially for untargeted attacks, the SCME outperforms SOTA methods by 11.43\% on average for five baseline datasets.

Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast optimization space and require a large number of queries, hence exhibiting limited practical impacts in real-world scenarios. In this paper, we propose a novel black-box attack strategy, Conditional Diffusion Model Attack (CDMA), to improve the query efficiency of generating AEs under query-limited situations. The key insight of CDMA is to formulate the task of AE synthesis as a distribution transformation problem, i.e., benign examples and their corresponding AEs can be regarded as coming from two distinctive distributions and can transform from each other with a particular converter. Unlike the conventional \textit{query-and-optimization} approach, we generate eligible AEs with direct conditional transform using the aforementioned data converter, which can significantly reduce the number of queries needed. CDMA adopts the conditional Denoising Diffusion Probabilistic Model as the converter, which can learn the transformation from clean samples to AEs, and ensure the smooth development of perturbed noise resistant to various defense strategies. We demonstrate the effectiveness and efficiency of CDMA by comparing it with nine state-of-the-art black-box attacks across three benchmark datasets. On average, CDMA can reduce the query count to a handful of times; in most cases, the query count is only ONE. We also show that CDMA can obtain $>99\%$ attack success rate for untarget attacks over all datasets and targeted attack over CIFAR-10 with the noise budget of $\epsilon=16$.

As the adoption of IoT-based smart homes continues to grow, the importance of addressing potential conflicts becomes increasingly vital for ensuring seamless functionality and user satisfaction. In this survey, we introduce a novel conflict taxonomy, complete with formal definitions of each conflict type that may arise within the smart home environment. We design an advanced conflict model to effectively categorize these conflicts, setting the stage for our in-depth review of recent research in the field. By employing our proposed model, we systematically classify conflicts and present a comprehensive overview of cutting-edge conflict detection approaches. This extensive analysis allows us to highlight similarities, clarify significant differences, and uncover prevailing trends in conflict detection techniques. In conclusion, we shed light on open issues and suggest promising avenues for future research to foster accelerated development and deployment of IoT-based smart homes, ultimately enhancing their overall performance and user experience., Comment: 38 pages, 4 figures, 2 tables

The large population of wireless users is a key driver of data-crowdsourced Machine Learning (ML). However, data privacy remains a significant concern. Federated Learning (FL) encourages data sharing in ML without requiring data to leave users' devices but imposes heavy computation and communications overheads on mobile devices. Hierarchical FL (HFL) alleviates this problem by performing partial model aggregation at edge servers. HFL can effectively reduce energy consumption and latency through effective resource allocation and appropriate user assignment. Nevertheless, resource allocation in HFL involves optimizing multiple variables, and the objective function should consider both energy consumption and latency, making the development of resource allocation algorithms very complicated. Moreover, it is challenging to perform user assignment, which is a combinatorial optimization problem in a large search space. This article proposes a spectrum resource optimization algorithm (SROA) and a two-stage iterative algorithm (TSIA) for HFL. Given an arbitrary user assignment pattern, SROA optimizes CPU frequency, transmit power, and bandwidth to minimize system cost. TSIA aims to find a user assignment pattern that considerably reduces the total system cost. Experimental results demonstrate the superiority of the proposed HFL framework over existing studies in energy and latency reduction., Comment: Under review by IEEE Transactions on Communications

In this paper, we aim to explore the use of uplink semantic communications with the assistance of UAV in order to improve data collection effiicency for metaverse users in remote areas. To reduce the time for uplink data collection while balancing the trade-off between reconstruction quality and computational energy cost, we propose a hybrid action reinforcement learning (RL) framework to make decisions on semantic model scale, channel allocation, transmission power, and UAV trajectory. The variables are classified into discrete type and continuous type, which are optimized by two different RL agents to generate the combined action. Simulation results indicate that the proposed hybrid action reinforcement learning framework can effectively improve the efficiency of uplink semantic data collection under different parameter settings and outperforms the benchmark scenarios., Comment: This paper appears in IEEE Global Communications Conference (GLOBECOM) 2023

Knowledge graph completion (KGC) is the task of inferencing missing facts from any given knowledge graphs (KG). Previous KGC methods typically represent knowledge graph entities and relations as trainable continuous embeddings and fuse the embeddings of the entity $h$ (or $t$) and relation $r$ into hidden representations of query $(h, r, ?)$ (or $(?, r, t$)) to approximate the missing entities. To achieve this, they either use shallow linear transformations or deep convolutional modules. However, the linear transformations suffer from the expressiveness issue while the deep convolutional modules introduce unnecessary inductive bias, which could potentially degrade the model performance. Thus, we propose a novel Transformer-based Patch Refinement Model (PatReFormer) for KGC. PatReFormer first segments the embedding into a sequence of patches and then employs cross-attention modules to allow bi-directional embedding feature interaction between the entities and relations, leading to a better understanding of the underlying KG. We conduct experiments on four popular KGC benchmarks, WN18RR, FB15k-237, YAGO37 and DB100K. The experimental results show significant performance improvement from existing KGC methods on standard KGC evaluation metrics, e.g., MRR and H@n. Our analysis first verifies the effectiveness of our model design choices in PatReFormer. We then find that PatReFormer can better capture KG information from a large relation embedding dimension. Finally, we demonstrate that the strength of PatReFormer is at complex relation types, compared to other KGC models, Comment: Accepted by ADMA 2023, oral

Knowledge Graph Completion (KGC) often requires both KG structural and textual information to be effective. Pre-trained Language Models (PLMs) have been used to learn the textual information, usually under the fine-tune paradigm for the KGC task. However, the fine-tuned PLMs often overwhelmingly focus on the textual information and overlook structural knowledge. To tackle this issue, this paper proposes CSProm-KG (Conditional Soft Prompts for KGC) which maintains a balance between structural information and textual knowledge. CSProm-KG only tunes the parameters of Conditional Soft Prompts that are generated by the entities and relations representations. We verify the effectiveness of CSProm-KG on three popular static KGC benchmarks WN18RR, FB15K-237 and Wikidata5M, and two temporal KGC benchmarks ICEWS14 and ICEWS05-15. CSProm-KG outperforms competitive baseline models and sets new state-of-the-art on these benchmarks. We conduct further analysis to show (i) the effectiveness of our proposed components, (ii) the efficiency of CSProm-KG, and (iii) the flexibility of CSProm-KG., Comment: Accepted by ACL 2023 Findings, Long Paper

Generative AI (GAI) models have been rapidly advancing, with a wide range of applications including intelligent networks and mobile AI-generated content (AIGC) services. Despite their numerous applications and potential, such models create opportunities for novel security challenges. In this paper, we examine the challenges and opportunities of GAI in the realm of the security of intelligent network AIGC services such as suggesting security policies, acting as both a ``spear'' for potential attacks and a ``shield'' as an integral part of various defense mechanisms. First, we present a comprehensive overview of the GAI landscape, highlighting its applications and the techniques underpinning these advancements, especially large language and diffusion models. Then, we investigate the dynamic interplay between GAI's spear and shield roles, highlighting two primary categories of potential GAI-related attacks and their respective defense strategies within wireless networks. A case study illustrates the impact of GAI defense strategies on energy consumption in an image request scenario under data poisoning attack. Our results show that by employing an AI-optimized diffusion defense mechanism, energy can be reduced by 8.7%, and retransmission count can be decreased from 32 images, without defense, to just 6 images, showcasing the effectiveness of GAI in enhancing network security.

Unmanned aerial vehicles (UAVs) are promising for providing communication services due to their advantages in cost and mobility, especially in the context of the emerging Metaverse and Internet of Things (IoT). This paper considers a UAV-assisted Metaverse network, in which UAVs extend the coverage of the base station (BS) to collect the Metaverse data generated at roadside units (RSUs). Specifically, to improve the data collection efficiency, resource allocation and trajectory control are integrated into the system model. The time-dependent nature of the optimization problem makes it non-trivial to be solved by traditional convex optimization methods. Based on the proposed UAV-assisted Metaverse network system model, we design a hybrid framework with reinforcement learning and convex optimization to {cooperatively} solve the time-sequential optimization problem. Simulation results show that the proposed framework is able to reduce the mission completion time with a given transmission power resource., Comment: This paper appears in IEEE Network magazine

Metaverse is expected to create a virtual world closely connected with reality to provide users with immersive experience with the support of 5G high data rate communication technique. A huge amount of data in physical world needs to be synchronized to the virtual world to provide immersive experience for users, and there will be higher requirements on coverage to include more users into Metaverse. However, 5G signal suffers severe attenuation, which makes it more expensive to maintain the same coverage. Unmanned aerial vehicle (UAV) is a promising candidate technique for future implementation of Metaverse as a low-cost and high-mobility platform for communication devices. In this paper, we propose a proximal policy optimization (PPO) based double-agent cooperative reinforcement learning method for channel allocation and trajectory control of UAV to collect and synchronize data from the physical world to the virtual world, and expand the coverage of Metaverse services economically. Simulation results show that our proposed method is able to achieve better performance compared to the benchmark approaches.

Machine learning (ML) is a widely accepted means for supporting customized services for mobile devices and applications. Federated Learning (FL), which is a promising approach to implement machine learning while addressing data privacy concerns, typically involves a large number of wireless mobile devices to collect model training data. Under such circumstances, FL is expected to meet stringent training latency requirements in the face of limited resources such as demand for wireless bandwidth, power consumption, and computation constraints of participating devices. Due to practical considerations, FL selects a portion of devices to participate in the model training process at each iteration. Therefore, the tasks of efficient resource management and device selection will have a significant impact on the practical uses of FL. In this paper, we propose a spectrum allocation optimization mechanism for enhancing FL over a wireless mobile network. Specifically, the proposed spectrum allocation optimization mechanism minimizes the time delay of FL while considering the energy consumption of individual participating devices; thus ensuring that all the participating devices have sufficient resources to train their local models. In this connection, to ensure fast convergence of FL, a robust device selection is also proposed to help FL reach convergence swiftly, especially when the local datasets of the devices are not independent and identically distributed (non-iid). Experimental results show that (1) the proposed spectrum allocation optimization method optimizes time delay while satisfying the individual energy constraints; (2) the proposed device selection method enables FL to achieve the fastest convergence on non-iid datasets., Comment: This paper is accepted by IEEE/ACM Transactions on Networking

To prevent fake news images from misleading the public, it is desirable not only to verify the authenticity of news images but also to trace the source of fake news, so as to provide a complete forensic chain for reliable fake news detection. To simultaneously achieve the goals of authenticity verification and source tracing, we propose a traceable and authenticable image tagging approach that is based on a design of Decoupled Invertible Neural Network (DINN). The designed DINN can simultaneously embed the dual-tags, \textit{i.e.}, authenticable tag and traceable tag, into each news image before publishing, and then separately extract them for authenticity verification and source tracing. Moreover, to improve the accuracy of dual-tags extraction, we design a parallel Feature Aware Projection Model (FAPM) to help the DINN preserve essential tag information. In addition, we define a Distance Metric-Guided Module (DMGM) that learns asymmetric one-class representations to enable the dual-tags to achieve different robustness performances under malicious manipulations. Extensive experiments, on diverse datasets and unseen manipulations, demonstrate that the proposed tagging approach achieves excellent performance in the aspects of both authenticity verification and source tracing for reliable fake news detection and outperforms the prior works.

Deep Neural Networks (DNNs) have been widely applied in Internet of Things (IoT) systems for various tasks such as image classification and object detection. However, heavyweight DNN models can hardly be deployed on edge devices due to limited computational resources. In this paper, an edge-cloud cooperation framework is proposed to improve inference accuracy while maintaining low inference latency. To this end, we deploy a lightweight model on the edge and a heavyweight model on the cloud. A reinforcement learning (RL)-based DNN compression approach is used to generate the lightweight model suitable for the edge from the heavyweight model. Moreover, a supervised learning (SL)-based offloading strategy is applied to determine whether the sample should be processed on the edge or on the cloud. Our method is implemented on real hardware and tested on multiple datasets. The experimental results show that (1) The sizes of the lightweight models obtained by RL-based DNN compression are up to 87.6% smaller than those obtained by the baseline method; (2) SL-based offloading strategy makes correct offloading decisions in most cases; (3) Our method reduces up to 78.8% inference latency and achieves higher accuracy compared with the cloud-only strategy., Comment: This paper appears in the Proceedings of 2022 IEEE International Conferences on Internet of Things (iThings)

This research aims to make metaverse characters more realistic by adding lip animations learnt from videos in the wild. To achieve this, our approach is to extend Tacotron 2 text-to-speech synthesizer to generate lip movements together with mel spectrogram in one pass. The encoder and gate layer weights are pre-trained on LJ Speech 1.1 data set while the decoder is retrained on 93 clips of TED talk videos extracted from LRS 3 data set. Our novel decoder predicts displacement in 20 lip landmark positions across time, using labels automatically extracted by OpenFace 2.0 landmark predictor. Training converged in 7 hours using less than 5 minutes of video. We conducted ablation study for Pre/Post-Net and pre-trained encoder weights to demonstrate the effectiveness of transfer learning between audio and visual speech data.

With the development of blockchain and communication techniques, the Metaverse is considered as a promising next-generation Internet paradigm, which enables the connection between reality and the virtual world. The key to rendering a virtual world is to provide users with immersive experiences and virtual avatars, which is based on virtual reality (VR) technology and high data transmission rate. However, current VR devices require intensive computation and communication, and users suffer from high delay while using wireless VR devices. To build the connection between reality and the virtual world with current technologies, mobile augmented reality (MAR) is a feasible alternative solution due to its cheaper communication and computation cost. This paper proposes an MAR-based connection model for the Metaverse, and proposes a communication resources allocation algorithm based on outer approximation (OA) to achieve the best utility. Simulation results show that our proposed algorithm is able to provide users with basic MAR services for the Metaverse, and outperforms the benchmark greedy algorithm., Comment: A full paper published in IEEE Global Communications Conference (GLOBECOM) 2022

Knowledge Graph Completion (KGC) has been recently extended to multiple knowledge graph (KG) structures, initiating new research directions, e.g. static KGC, temporal KGC and few-shot KGC. Previous works often design KGC models closely coupled with specific graph structures, which inevitably results in two drawbacks: 1) structure-specific KGC models are mutually incompatible; 2) existing KGC methods are not adaptable to emerging KGs. In this paper, we propose KG-S2S, a Seq2Seq generative framework that could tackle different verbalizable graph structures by unifying the representation of KG facts into "flat" text, regardless of their original form. To remedy the KG structure information loss from the "flat" text, we further improve the input representations of entities and relations, and the inference algorithm in KG-S2S. Experiments on five benchmarks show that KG-S2S outperforms many competitive baselines, setting new state-of-the-art performance. Finally, we analyze KG-S2S's ability on the different relations and the Non-entity Generations., Comment: COLING 2022 Main Conference

Face presentation attack detection (PAD) has been extensively studied by research communities to enhance the security of face recognition systems. Although existing methods have achieved good performance on testing data with similar distribution as the training data, their performance degrades severely in application scenarios with data of unseen distributions. In situations where the training and testing data are drawn from different domains, a typical approach is to apply domain adaptation techniques to improve face PAD performance with the help of target domain data. However, it has always been a non-trivial challenge to collect sufficient data samples in the target domain, especially for attack samples. This paper introduces a teacher-student framework to improve the cross-domain performance of face PAD with one-class domain adaptation. In addition to the source domain data, the framework utilizes only a few genuine face samples of the target domain. Under this framework, a teacher network is trained with source domain samples to provide discriminative feature representations for face PAD. Student networks are trained to mimic the teacher network and learn similar representations for genuine face samples of the target domain. In the test phase, the similarity score between the representations of the teacher and student networks is used to distinguish attacks from genuine ones. To evaluate the proposed framework under one-class domain adaptation settings, we devised two new protocols and conducted extensive experiments. The experimental results show that our method outperforms baselines under one-class domain adaptation settings and even state-of-the-art methods with unsupervised domain adaptation.

With the increasing adoption of data-hungry machine learning algorithms, personal data privacy has emerged as one of the key concerns that could hinder the success of digital transformation. As such, Privacy-Preserving Machine Learning (PPML) has received much attention from both academia and industry. However, organizations are faced with the dilemma that, on the one hand, they are encouraged to share data to enhance ML performance, but on the other hand, they could potentially be breaching the relevant data privacy regulations. Practical PPML typically allows multiple participants to individually train their ML models, which are then aggregated to construct a global model in a privacy-preserving manner, e.g., based on multi-party computation or homomorphic encryption. Nevertheless, in most important applications of large-scale PPML, e.g., by aggregating clients' gradients to update a global model for federated learning, such as consumer behavior modeling of mobile application services, some participants are inevitably resource-constrained mobile devices, which may drop out of the PPML system due to their mobility nature. Therefore, the resilience of privacy-preserving aggregation has become an important problem to be tackled. In this paper, we propose a scalable privacy-preserving aggregation scheme that can tolerate dropout by participants at any time, and is secure against both semi-honest and active malicious adversaries by setting proper system parameters. By replacing communication-intensive building blocks with a seed homomorphic pseudo-random generator, and relying on the additive homomorphic property of Shamir secret sharing scheme, our scheme outperforms state-of-the-art schemes by up to 6.37$\times$ in runtime and provides a stronger dropout-resilience. The simplicity of our scheme makes it attractive both for implementation and for further improvements., Comment: 16 pages, 5 figures. Accepted by IEEE Transactions on Information Forensics and Security

Over the recent years, with the increasing adoption of Federated Learning (FL) algorithms and growing concerns over personal data privacy, Privacy-Preserving Federated Learning (PPFL) has attracted tremendous attention from both academia and industry. Practical PPFL typically allows multiple participants to individually train their machine learning models, which are then aggregated to construct a global model in a privacy-preserving manner. As such, Privacy-Preserving Aggregation (PPAgg) as the key protocol in PPFL has received substantial research interest. This survey aims to fill the gap between a large number of studies on PPFL, where PPAgg is adopted to provide a privacy guarantee, and the lack of a comprehensive survey on the PPAgg protocols applied in FL systems. In this survey, we review the PPAgg protocols proposed to address privacy and security issues in FL systems. The focus is placed on the construction of PPAgg protocols with an extensive analysis of the advantages and disadvantages of these selected PPAgg protocols and solutions. Additionally, we discuss the open-source FL frameworks that support PPAgg. Finally, we highlight important challenges and future research directions for applying PPAgg to FL systems and the combination of PPAgg with other technologies for further security improvement., Comment: 20 pages, 10 figures. Accepted by IEEE Transactions on Big Data

Timely sharing of electronic health records (EHR) across providers is essential and significance in facilitating medical researches and prompt patients' care. With sharing, it is crucial that patients can control who can access their data and when, and guarantee the security and privacy of their data. In current literature, various system models, cryptographic techniques and access control mechanisms are proposed which requires patient's consent before sharing. However, they mostly focus on patient is available to authorize the access of the EHR upon requested. This is impractical given that the patient may not always be in a good state to provide this authorization, eg, being unconscious and requires immediate medical attention. To address this gap, this paper proposes an efficient and secure protocol for the pre-delegation of authorization to multi-party for the access of the EHR when patient is unavailable to do so. The solution adopts a novel approach to combine self-sovereign identity concepts and framework with secure multi-party computation to enable secure identity and authorization verification. Theoretical analysis showed that it increased the efficiency of the protocol and verification processes to ensure the security and privacy of patient's data.

Advances in emerging technologies have accelerated digital transformation with the pervasive digitalization of the economy and society, driving innovations such as smart cities, industry 4.0 and FinTech. Unlike digitization, digitalization is a transformation to improve processes by leveraging digital technologies and digitized data. The cyberspace has evolved from a hardware internetworking infrastructure to the notion of a virtual environment, transforming how people, business and government interact and operate. Through this transformation, lots of personal data are captured which individuals have no ownership or control over, threatening their privacy. It is therefore necessary for the data owners to have control over the ownership, custody and utilization of their data and to protect one's digital assets and identity through proper data governance, cybersecurity control and privacy protection. This results in the notions of data sovereignty and digital sovereignty - two conceptually related terms, but different focuses. This paper first explains these two concepts in terms of their guiding principles, laws and regulations requirements, and analyse and discuss the technical challenges of implementing these requirements. Next, to understand the emerging trend shift in digital sovereignty towards individuals to take complete control of the security and privacy of their own digital assets, this paper conducts a systematic study and analysis of Self-Sovereign Identity, and discuss existing solutions and point out that an efficient key management system, scalability and interoperability of the solutions and well established standards are some of its challenges and open problems to wide deployments.

A city is a large human settlement that serves the people who live there, and a smart city is a concept of how cities might better serve their residents through new forms of technology. In this paper, we focus on four major smart city domains according to Maslow's hierarchy of needs: smart utility, smart transportation, smart homes, and smart healthcare. Numerous IoT applications have been developed to achieve the intelligence that we desire in our smart domains, ranging from personal gadgets such as health trackers and smart watches to large-scale industrial IoT systems such as nuclear and energy management systems. However, many of the existing smart city IoT solutions can be made better by considering the suitability of their security strategies. Inappropriate system security designs generally occur in two scenarios: first, system designers recognize the importance of security but are unsure of where, when, or how to implement it; and second, system designers try to fit traditional security designs to meet the smart city security context. Thus, the objective of this paper is to provide application designers with the missing security link they may need to improve their security designs. By evaluating the specific context of each smart city domain and the context-specific security requirements, we aim to provide directions on when, where, and how they should implement security strategies and the possible security challenges they need to consider. In addition, we present a new perspective on security issues in smart cities from a data-centric viewpoint by referring to the reference architecture, the Activity-Network-Things (ANT)-centric architecture, built upon the concept of "security in a zero-trust environment". By doing so, we reduce the security risks posed by new system interactions or unanticipated user behaviors while avoiding the hassle of regularly upgrading security models., Comment: Submitted to IEEE IoT Journal

Face presentation attack detection (PAD) is an essential measure to protect face recognition systems from being spoofed by malicious users and has attracted great attention from both academia and industry. Although most of the existing methods can achieve desired performance to some extent, the generalization issue of face presentation attack detection under cross-domain settings (e.g., the setting of unseen attacks and varying illumination) remains to be solved. In this paper, we propose a novel framework based on asymmetric modality translation for face presentation attack detection in bi-modality scenarios. Under the framework, we establish connections between two modality images of genuine faces. Specifically, a novel modality fusion scheme is presented that the image of one modality is translated to the other one through an asymmetric modality translator, then fused with its corresponding paired image. The fusion result is fed as the input to a discriminator for inference. The training of the translator is supervised by an asymmetric modality translation loss. Besides, an illumination normalization module based on Pattern of Local Gravitational Force (PLGF) representation is used to reduce the impact of illumination variation. We conduct extensive experiments on three public datasets, which validate that our method is effective in detecting various types of attacks and achieves state-of-the-art performance under different evaluation protocols.