The emergence of Large Language Models (LLMs) in Multi-Agent Systems (MAS) has opened new possibilities for artificial intelligence, yet current implementations face significant challenges in resource management, task coordination, and system efficiency. While existing frameworks demonstrate the potential of LLM-based agents in collaborative problem-solving, they often lack sophisticated mechanisms for parallel execution and dynamic task management. This paper introduces DynTaskMAS, a novel framework that orchestrates asynchronous and parallel operations in LLM-based MAS through dynamic task graphs. The framework features four key innovations: (1) a Dynamic Task Graph Generator that intelligently decomposes complex tasks while maintaining logical dependencies, (2) an Asynchronous Parallel Execution Engine that optimizes resource utilization through efficient task scheduling, (3) a Semantic-Aware Context Management System that enables efficient information sharing among agents, and (4) an Adaptive Workflow Manager that dynamically optimizes system performance. Experimental evaluations demonstrate that DynTaskMAS achieves significant improvements over traditional approaches: a 21-33% reduction in execution time across task complexities (with higher gains for more complex tasks), a 35.4% improvement in resource utilization (from 65% to 88%), and near-linear throughput scaling up to 16 concurrent agents (3.47× improvement for 4× agents). Our framework establishes a foundation for building scalable, high-performance LLM-based multi-agent systems capable of handling complex, dynamic tasks efficiently.

The prevailing Gaussian Splatting has been adapted for image representation and compression by GaussianImage recently, achieving impressive rendering speeds of 1500–2000 FPS. However, it falls short in rate-distortion performance compared to current state-of-the-art image codecs. We attribute this to its explicit representation and tile-based rasterization process which demands a more efficient utilization of 2D Gaussians for improved performance. In this work, we propose a spectrum-adaptive distribution method to allocate Gaussians in alignment with the complexity of varying image regions. Additionally, we introduce a gradient-based growing strategy for Gaussians to further refine their distribution. Experimental results show that our approach outperforms GaussianImage in image representation quality while maintaining comparable training and rendering speeds. Moreover, by integrating a transform-quantization pipeline for the position attributes of Gaussians, our approach delivers a better rate-distortion curve compared to the INR-based codecs such as COIN and COIN++.

Existing solutions to the joint problem of image deblurring and compression typically adopt a straightforward sequential pipeline, where the two task are handled independently by either compressing the blurred image first or by deblurring before compression. However, such decoupled strategies often suffer from error accumulation and increased computational overhead, leading to suboptimal performance in both compression and restoration. In this work, we propose a joint solution to simultaneously address image deblurring and compression within a learned image compression framework, with the capacity to encode a compact bitstream of the underlying sharp image from its blurred observation. Specifically, our framework has a two-branch encoder architecture, consisting of a main branch and a guidance branch. The guidance branch extracts blur-aware features from the blurry image, which are then fused into the main branch to assist in encoding features that are both bitrate-efficient and essential for accurate sharp restoration. Furthermore, we enhance the fused features in both the spatial and frequency domains. In particular, a JPEG-like transform-quantization mechanism is adopted to modulate the fused features using differentiable quantization matrices in the frequency domain. Extensive experiments on widely-used deblurring datasets demonstrate that our joint solution achieves superior rate-distortion performance, while significantly reducing inference latency compared to existing sequential approaches.

Large language models (LLMs) have demonstrated proficiency in various language tasks but encounter difficulties in specific domain or scenario. These challenges are mitigated through prompt engineering techniques such as retrieval-augmented generation, which improves performance by integrating contextual information. However, concerns regarding the privacy implications of context-aware reasoning architectures persist, particularly regarding the transmission of sensitive data to LLMs service providers, potentially compromising personal privacy. To mitigate these challenges, this paper introduces Tex-tual Differential Privacy, a novel paradigm aimed at safeguarding user privacy in LLMs-based context-aware reasoning. The proposed Differential Embedding Hash algorithm anonymizes sensitive information while maintaining the reasoning capability of LLMs. Additionally, a quantification scheme for privacy loss is proposed to better understand the trade-off between privacy protection and loss. Through rigorous analysis and experimentation, the effectiveness and robustness of the proposed paradigm in mitigating privacy risks associated with context-aware reasoning tasks are demonstrated. This paradigm addresses privacy concerns in context-aware reasoning architectures, enhancing the trust and utility of LLMs in various applications.

Surface electromyography (sEMG) signals find extensive applications in medicine and bioengineering, particularly in rehabilitation and assistive technologies. Gesture classification using sEMG poses challenges such as noise removal, feature extraction, and personalized classification to accommodate individual variations in human physiology. To address these challenges, we propose an sEMG-based gesture classification method by leveraging the nearest centroid classifier and guiding the generation of centroids generated with Soft-DTW as a loss function. Additionally, we apply denoising techniques to the original sEMG signals, including DC offset removal, bandpass filtering, full-wave rectification, and linear envelope extraction. Additionally, we propose a cubic spline for downsampling. With a 1% downsampling rate, our method achieves 89.1% on average and 90.5% at peak and outperforms the state-of-the-art methods.

Data aggregation management is paramount in data-driven distributed systems. Conventional solutions premised on centralized networks grapple with security challenges concerning authenticity, confidentiality, integrity, and privacy. Recently, distributed ledger technology has gained popularity for its decentralized nature to facilitate overcoming these challenges. Nevertheless, insufficient identity management introduces risks like impersonation and unauthorized access. In this paper, we propose Degator, a data aggregation management framework that leverages self-sovereign identity and functions in decentralized networks to address security concerns and mitigate identity-related risks. We formulate fully decentralized aggregation protocols for data persistence and acquisition in Degator. Degator is compatible with existing data persistence methods, and supports cost-effective data acquisition minimizing dependency on distributed ledgers. We also conduct a formal analysis to elucidate the mechanism of Degator to tackle current security challenges in conventional data aggregation management. Furthermore, we showcase the applicability of Degator through its application in the management of decentralized neuroscience data aggregation and demonstrate its scalability via performance evaluation.

Best practices of self-sovereign identity (SSI) are being intensively explored in academia and industry. Reusable solutions obtained from best practices are generalized as architectural patterns for systematic analysis and design reference, which significantly boosts productivity and increases the dependability of future implementations. For security-sensitive projects, architects make architectural decisions with careful consideration of security issues and solutions based on formal analysis and experiment results. In this paper, we propose a model-driven security analysis framework for analyzing architectural patterns of SSI systems with respect to a threat model built on our investigation of real-world security concerns. Our framework mechanizes a modeling language to formalize patterns and threats with security properties in temporal logic and automatically generates programs for verification via model checking. Besides, we present typical vulnerable patterns verified by SecureSSI, a standalone integrated development environment, integrating commonly used pattern and attacker models to practicalize our framework.

Security infrastructures heavily rely on public key cryptography. With the emergence of quantum threats, NIST has been standardizing post-quantum cryptographic algorithms like CRYSTALS-Kyber. However, a major challenge in public-key cryptography is establishing a secure connection between verifiable information of specific entities and public keys. Traditionally, this challenge is addressed through Public Key Infrastructures (PKIs). Nevertheless, the current PKIs suffer from security and performance issues due to the requirement of central authorities. In this paper, we propose Inj-Kyber, a novel algorithm enhancing Kyber with information injection. Inj-Kyber achieves robust entity-key binding by injecting verifiable information into public keys while ensuring equivalent security to Kyber. Additionally, we showcase the applicability of Inj-Kyber through Bio-KEM, a KEM framework leveraging Inj-Kyber and biometric authentication to protect public keys via biometric information binding.

Online signature verification plays a pivotal role in security infrastructures. However, conventional online signature verification models pose significant risks to data privacy, especially during training processes. To mitigate these concerns, we propose a novel federated learning framework that leverages 1-D Convolutional Neural Networks (CNN) for online signature verification. Furthermore, our experiments demonstrate the effectiveness of our framework regarding 1-D CNN and federated learning. Particularly, the experiment results highlight that our framework 1) minimizes local computational resources; 2) enhances transfer effects with substantial initialization data; 3) presents remarkable scalability. The centralized 1-D CNN model achieves an Equal Error Rate (EER) of 3.33% and an accuracy of 96.25%. Meanwhile, configurations with 2, 5, and 10 agents yield EERs of 5.42%, 5.83%, and 5.63%, along with accuracies of 95.21%, 94.17%, and 94.06%, respectively.

Self-sovereign identity (SSI) has gained a large amount of interest. It enables physical entities to retain ownership and control of their digital identities, forming a conceptually decentralized architecture. With the support of distributed ledger technology (DLT), it is possible to implement this conceptually decentralized architecture in practice and further bring technical advantages such as privacy protection, security enhancement, and high availability. However, developing such a relatively new identity model has high costs and risks with uncertainty. To facilitate the use of the DLT-based SSI in practice, we formulate Self-Sovereign Identity as a Service (SSIaaS), a concept that enables a system, especially a system cluster, to readily adopt SSI as its identity model for identification, authentication, and authorization. We propose a practical architecture by elaborating the service concept, SSI, and DLT to implement SSIaaS platforms and SSI services. Besides, we present an architecture for constructing and customizing SSI services with a set of architectural patterns and provide corresponding evaluations. Furthermore, we demonstrate the feasibility of our proposed architecture in practice with Selfid, an SSIaaS platform based on our proposed architecture.

Decentralized systems have been widely developed and applied to address security and privacy issues in centralized systems, especially since the advancement of distributed ledger technology. However, it is challenging to ensure their correct functioning with respect to their designs and minimize the technical risk before the delivery. Although formal methods have made significant progress over the past decades, a feasible solution based on formal methods from a development process perspective has not been well developed. In this paper, we formulate an iterative and incremental development process, named formalism-driven development (FDD), for developing provably correct decentralized systems under the guidance of formal methods. We also present a framework named Seniz, to practicalize FDD with a new modeling language and scaffolds. Furthermore, we conduct case studies to demonstrate the effectiveness of FDD in practice with the support of Seniz.

As the infrastructure to provide support for distributed database management systems, the distributed database platform is very important to unify the management of data distributed in intricate environments. However, a traditional distributed database platform with centralized entities faces diverse and serious threats when the central entity is compromised. Consensus mechanisms in distributed ledger technology (DLT) can enhance the capability of defending threats by decentralizing the platform, but the efficiency and cost of consensus mechanisms in classic blockchain techniques are notable issues. In this paper, we propose a novel decentralized database platform, named Dagbase, with the support of an efficient and cost-effective consensus mechanism that uses the directed acyclic graph (DAG) as the structure. Dagbase decentralizes the management and distributes data to prevent threats in untrustworthy environments, which gains benefits from recent DLT. The performance of near-native data reading and high-efficiency data writing is ensured by a layered architecture and DAG-based consensus. Furthermore, we ensure flexibility by decoupling the consensus mechanism from the architecture. Dagbase is also easy-to-use and can be integrated with mainstream database products seamlessly on account of great interoperability. The implementation demonstrates our work and the security and performance analysis are enforced for evaluation.