Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs), especially for knowledge-intensive tasks.Despite its advantages, current RAG methods often struggle to fully exploit knowledge during generation.In particular, the synergy between the model's internal parametric knowledge and external retrieved knowledge remains limited.Retrieved contents may sometimes mislead generation, while certain generated content can guide the model toward more accurate outputs.In this work, we propose Collaborative Chainof-Agents, a framework designed to enhance explicitly synergy over both parametric and retrieved knowledge.Specifically, we first introduce CoCoA-zero, a multi-agent RAG framework that first performs conditional knowledge induction and then reasons answers.Building on this, we develop CoCoA, a long-chain training strategy that synthesizes extended multiagent reasoning trajectories from CoCoA-zero to fine-tune the LLM.This strategy enhances the model's capability to explicitly integrate and jointly leverage parametric and retrieved knowledge.Experimental results demonstrate the superiority of CoCoA in open-domain QA and multi-hop QA.Code is public 1 .

The System Wide Information Management (SWIM) system serves as an advanced platform for managing and sharing diverse aviation data, such as aeronautical, flight, and meteorological information. With the exponential growth of aviation data, ensuring data security and privacy within SWIM has become increasingly important. Ciphertext-Policy Attribute-Based Encryption (CP-ABE) is widely regarded as an effective cryptographic technique for ensuring secure and private data access. However, traditional CP-ABE schemes rely on computationally expensive bilinear pairings, which are unsuitable for resource-constrained aviation Internet of Things application scenarios in SWIM, such as Aircraft Access to SWIM. To address this limitation, we propose a lightweight multi-authority CP-ABE scheme based on dynamic attributes. This scheme replaces bilinear pairing operations with efficient scalar multiplication on elliptic curve points and outsources most decryption operations to outsourcing decryption nodes, thereby significantly reducing computational overhead. In addition, this scheme introduces a dynamic attribute mechanism to support fine-grained access control, and outsources data verification and attribute revocation to the blockchain to ensure data integrity. Security analysis shows that our scheme achieves indistinguishability under adaptive chosen-ciphertext attacks and is resistant to collusion attacks. Experimental evaluations further demonstrate that our scheme significantly enhances computational and communication efficiency.

As a global civil aviation information-sharing service platform, cross-domain authentication of system wide information management (SWIM) has attracted much attention.Due to the inability of existing authentication schemes to meet the needs of lightweight users such as aircraft for secure cross-domain access to SWIM in the aircraft access to SWIM application, we propose a lightweight blockchain-assisted cross-domain authentication scheme for SWIM.The scheme uses certificateless cryptography to generate user private keys and achieves mutual authentication and key agreement for cross-domain users based on the elliptic curve Diffie-Hellman.Additionally, cross-domain users share authentication public parameters and anonymous identity through a consortium blockchain, thereby protecting identity privacy and establishing trust among them.We use SVO logic to prove that the authentication protocol realises its design goals and utilise the formal verification tool Scyther to demonstrate the scheme's security.Compared to the four existing schemes, our scheme has lower computational and communication overhead.

Abstract The system wide information management (SWIM) system infrastructure layer uses information‐centric networking (ICN) to implement the cache routing and sharing of air traffic information data. The SWIM network searches and forwards routes on the basis of content names. The variable length, hierarchical name structure, and routing updates caused by the frequent publication and deletion of content make the implementation of fast name routing lookup algorithms a significant but arduous task. To address this problem, this study designed a name matching mechanism on the basis of the hybrid structure of the Bloom filter and the Tree. Compared with the traditional Bloom filter search scheme, this search mechanism reduces the quantity of Bloom filter insertion entries and reduces the possibility of hash collisions. Compared with the traditional Tree search scheme, the proposed mechanism can effectively solve the problem of numerous memory accesses caused by extremely long name prefixes, improving the query efficiency. In addition, the proposed composite structure is compared with several methods, such as DIPIT and NPT, by analyzing the effects of layering, global delay and search speed. The experimental results show that the proposed structure has a favourable performance in terms of storage overhead and search speed.

System wide information management (SWIM) is a platform to share and exchange information on the new air traffic management (ATM) services between different departments and systems in the civil aviation field. Through the connection of SWIM and various application services, a virtual information pool is formed to solve the interconnection issues of different systems. To ensure data security in the system and quick authentication of legitimate users, we propose a unified identity authentication scheme for SWIM. This scheme improves the security assertion markup language (SAML) cross-domain authentication model and integrates it with the public key infrastructure (PKI) authentication system and lightweight directory access protocol (LDAP). Experimental results show that this scheme realises the functions of user management, identity authentication, and cross-domain access, which can meet requirements of the SWIM gateway.

With the development of cloud computing, cloud security issues have recently gained traction in the research community. Although much of the efforts are focused on securing the operation system and virtual machine, or securing data storage inside a cloud system, this paper takes an alternative perspective to cloud security-the security of data migration between different clouds. First, we describe some threats when we are doing data migration. Second, we propose a security mechanism to deal with the security issues on data migration from one cloud to another. Third, we design a prototype to give the mechanism a brief implementation based on HDFS (Hadoop Distributed File System) and we do a series of tests to evaluate our prototype. Here, the solutions to securing data migration between clouds mainly involve in SSL negotiation, migration ticket design and block encryption in distributed file system and cluster parallel computing.