Parameter-efficient fine-tuning (PEFT) methods have emerged as a practical solution for adapting large foundation models to downstream tasks, reducing computational and memory costs by updating only a small subset of parameters. Among them, approaches like LoRA aim to strike a balance between efficiency and expressiveness, but often suffer from slow convergence and limited adaptation capacity due to their inherent low-rank constraints. This trade-off hampers the ability of PEFT methods to capture complex patterns needed for diverse tasks. To address these challenges, we propose FRoD, a novel fine-tuning method that combines hierarchical joint decomposition with rotational degrees of freedom. By extracting a globally shared basis across layers and injecting sparse, learnable perturbations into scaling factors for flexible full-rank updates, FRoD enhances expressiveness and efficiency, leading to faster and more robust convergence. On 20 benchmarks spanning vision, reasoning, and language understanding, FRoD matches full model fine-tuning in accuracy, while using only 1.72% of trainable parameters under identical training budgets.

With the development of air transportation, Space-Air-Ground Integrated Network (SAGIN) are playing an increasingly important role in optimizing air traffic management and enhancing flight safety for billions of passengers and trillions dollars of aviation industry. As the key technology of SAGIN, the Automatic Dependent Surveillance-Broadcast (ADS-B) system is widely used due to its simple operation, low construction cost, and high information accuracy. However, the security problems in ADS-B system, including lack of identity authentication between all communication links, crucial information transmitted in plaintext, and susceptibility to the single point of failure, have been serious obstacle to its wide application. Existing solutions fail to account for the unique characteristics of ADS-B and SAGIN, leading to inadequate security and poor performance in these specialized contexts. Aiming to solve the above issues and provide security and scalability for ADS-B system, we conduct the following research. Firstly, an enhanced identity-based broadcast signcryption (e-IBBSC) scheme is designed to keep crucial information confidential and all messages authenticated simultaneously. Secondly, we propose an efficient batch message authentication method combined with the Merkle tree and proposed e-IBBSC, significantly improving the ADS-B message utilization ratio from 1.35% to 74.10%. Thirdly, we utilize the sharding blockchain and Byzantine fault tolerance protocol to design the first sharding-based distributed management system for SAGIN that realizes fault tolerance and scalability. Finally, after a detailed security analysis and comprehensive performance evaluation, we demonstrate that our solution can achieve all proposed system goals including security, scalability, and high performance of 1s flight transaction processing latency and 62KTPS throughput.

Uncertainty estimation is essential for practical applications such as decision-making, risk assessment, and human-AI collaboration. However, Uncertainty estimation in open-ended question-answering (QA) tasks presents unique challenges. The output space for open-ended QA is vast and discrete, and the autoregressive nature of LLMs, combined with the rapid increase in model parameters, makes inference sampling significantly costly. An ideal uncertainty estimation for LLMs should meet two criteria: 1) incur no additional inference cost and 2) capture the semantic dependencies of token-level uncertainty within sequences. We propose a promising solution that converts redundancy into randomness in the extensive parameters of LLMs to quantify knowledge uncertainty. We can obtain token-level Monte Carlo samples without multiple inferences by introducing randomness during a single forward pass. We theoretically analyze the FLUE sampling method and employ a post-processing method to learn the state transitions from token uncertainty to sequence uncertainty. In open-ended question-answering tasks, we demonstrate that FLUE can achieve competitive performance in estimating the uncertainty of generated sentences without adding extra inference overhead.

As heterogeneous graph learning models have been widely applied, the risk of privacy leakage has become a growing concern. To address this issue, traditional federated learning frameworks are primarily employed in current methods to protect the privacy of heterogeneous graphs. However, these methods still encounter challenges, including vulnerabilities to membership inference attacks (MIAs) and a negative impact on data utility due to the addition of fixed noise. To overcome these limitations, we propose the privacy-preserving decentralized federated heterogeneous graph neural network (PDFHGN). In this model, a two-stage differential privacy protection approach based on edge embeddings and model gradients is employed to defend against both active and passive MIAs, thereby alleviating privacy concerns among clients. Additionally, an adaptive gradient clipping threshold is implemented to dynamically adjust the noise perturbation ranges, ensuring minimal impact on model utility. Furthermore, by leveraging the flexibility of the decentralized federated learning framework, the model maintains robustness across various types of client network topologies. Experimental validation on four real-world datasets demonstrates that our model strikes a favorable privacy-utility tradeoff while remaining adaptable to multiple client network structures.

A fundamental goal of Web 3.0 is to establish a decentralized network and application ecosystem, thereby enabling users to retain control over their data while promoting value exchange. However, the recent TRON-Steem takeover incident poses a significant threat to this vision. In this paper, we present a thorough empirical analysis of the TRON-Steem takeover incident. By conducting a fine-grained reconstruction of the stake and election snapshots within the Steem blockchain, one of the most prominent social-oriented blockchains, we quantify the marked shifts in decentralization pre and post the takeover incident, highlighting the severe threat that blockchain network takeovers pose to the decentralization principle of Web 3.0. Moreover, by employing heuristic methods to identify anomalous voters and conducting clustering analyses on voter behaviors, we unveil the underlying mechanics of takeover strategies employed in the TRON-Steem incident and suggest potential mitigation strategies, which contribute to the enhanced resistance of Web 3.0 networks against similar threats in the future. We believe the insights gleaned from this research help illuminate the challenges imposed by blockchain network takeovers in the Web 3.0 era, suggest ways to foster the development of decentralized technologies and governance, as well as to enhance the protection of Web 3.0 user rights.

Federated learning (FL) is inherently susceptible to privacy breaches and poisoning attacks. To tackle these challenges, researchers have separately devised secure aggregation mechanisms to protect data privacy and robust aggregation methods that withstand poisoning attacks. However, simultaneously addressing both concerns is challenging; secure aggregation facilitates poisoning attacks as most anomaly detection techniques require access to unencrypted local model updates, which are obscured by secure aggregation. Few recent efforts to simultaneously tackle both challenges offen depend on impractical assumption of non-colluding two-server setups that disrupt FL's topology, or three-party computation which introduces scalability issues, complicating deployment and application. To overcome this dilemma, this paper introduce a Dual Defense Federated learning (DDFed) framework. DDFed simultaneously boosts privacy protection and mitigates poisoning attacks, without introducing new participant roles or disrupting the existing FL topology. DDFed initially leverages cutting-edge fully homomorphic encryption (FHE) to securely aggregate model updates, without the impractical requirement for non-colluding two-server setups and ensures strong privacy protection. Additionally, we proposes a unique two-phase anomaly detection mechanism for encrypted model updates, featuring secure similarity computation and feedback-driven collaborative selection, with additional measures to prevent potential privacy breaches from Byzantine clients incorporated into the detection process. We conducted extensive experiments on various model poisoning attacks and FL scenarios, including both cross-device and cross-silo FL. Experiments on publicly available datasets demonstrate that DDFed successfully protects model privacy and effectively defends against model poisoning threats.

Federated learning is a computing paradigm that enhances privacy by enabling multiple parties to collaboratively train a machine learning model without revealing personal data. However, current research indicates that traditional federated learning platforms are unable to ensure privacy due to privacy leaks caused by the interchange of gradients. To achieve privacy-preserving federated learning, integrating secure aggregation mechanisms is essential. Unfortunately, existing solutions are vulnerable to recently demonstrated inference attacks such as the disaggregation attack. This paper proposesTAPFed, an approach for achieving privacy-preserving federated learning in the context of multiple decentralized aggregators with malicious actors.TAPFeduses a proposed threshold functional encryption scheme and allows for a certain number of malicious aggregators while maintaining security and privacy. We provide formal security and privacy analyses ofTAPFedand compare it to various baselines through experimental evaluation. Our results show thatTAPFedoffers equivalent performance in terms of model quality compared to state-of-the-art approaches while reducing transmission overhead by 29%-45% across different model training scenarios. Most importantly,TAPFedcan defend against recently demonstrated inference attacks caused by curious aggregators, which the majority of existing approaches are susceptible to.

The Transformer model has gained significant recognition for its remarkable computational capabilities and versatility, positioning itself as a fundamental component in numerous practical applications. However, the robustness of the Transformer model, specifically its stability and reliability under various types of adversarial attacks, is of utmost importance for its practical applicability. Furthermore, it offers valuable insights for the design of more efficient and secure models. In contrast with conventional investigations into adversarial robustness, our study focuses on the analysis of Positional Embeddings (PEs), a crucial component that sets the Transformer model apart from previous model architectures. Theoretical analysis of PEs has been limited due to previous predominantly empirical design, which includes features such as sinusoidal or linear patterns, learned or fixed characteristics, and absolute or relative measurements. Our investigation delves deep into potential vulnerabilities within PEs. Initially, we develop a set of input infection techniques that can be universally applied to exploit vulnerabilities present in the Transformer architecture and its variants. In addition, we propose a novel adversarial attack that manipulates the model by providing it with incorrect positional information, enabling an evasion attack. Significantly, in contrast to previous attacks that were limited to a single task, our conducted experiments involving time-series analysis, natural language processing, and computer vision indicate that the susceptibility of PEs could be universal and transferable. This finding serves as a significant warning for future Transformer-based model design, urging researchers to consider potential security risks inherent in the model’s structure.

Delegated-Proof-of-Stake (DPoS) blockchains, such as EOSIO, Steem and TRON, are governed by a committee of block producers elected via a coin-based voting system. We recently witnessed the first de facto blockchain takeover that happened between Steem and TRON. Within one hour of this incident, TRON founder took over the entire Steem committee, forcing the original Steem community to leave the blockchain that they maintained for years. This is a historical event in the evolution of blockchains and Web 3.0. Despite its significant disruptive impact, little is known about how vulnerable DPoS blockchains are in general to takeovers and the ways in which we can improve their resistance to takeovers.

Delegated-Proof-of-Stake (DPoS) blockchains are governed by a committee of dozens of members elected via coin-based voting mechanisms. This paper presents a large-scale empirical study of two critical characteristics, personal impact and participation rate, of three leading DPoS blockchains. Our findings reveal the existence of decisive voters whose votes can alter election outcomes, as well as the fact that almost half of the coins have never been used in committee elections. Our research contributes to demystifying the actual use of coin-based voting governance and offers novel insights into the potential security risks of DPoS blockchains.

Increasingly, information systems rely on computational, storage, and network resources deployed in third-party facilities such as cloud centers and edge nodes. Such an approach further exacerbates cybersecurity concerns constantly raised by numerous incidents of security and privacy attacks resulting in data leakage and identity theft, among others. These have, in turn, forced the creation of stricter security and privacy-related regulations and have eroded the trust in cyberspace. In particular, security-related services and infrastructures, such as Certificate Authorities (CAs) that provide digital certificate services and Third-Party Authorities (TPAs) that provide cryptographic key services, are critical components for establishing trust in crypto-based privacy-preserving applications and services. To address such trust issues, various transparency frameworks and approaches have been recently proposed in the literature. This paper proposes TAB framework that provides transparency and trustworthiness of third-party authority and third-party facilities using blockchain techniques for emerging crypto-based privacy-preserving applications. TAB employs the Ethereum blockchain as the underlying public ledger and also includes a novel smart contract to automate accountability with an incentive mechanism that motivates users to participate in auditing, and punishes unintentional or malicious behaviors. We implement TAB and show through experimental evaluation in the Ethereum official test network, Rinkeby, that the framework is efficient. We also formally show the security guarantee provided by TAB, and analyze the privacy guarantee and trustworthiness it provides.

Federated learning has emerged as a privacy-preserving machine learning approach where multiple parties can train a single model without sharing their raw training data. Federated learning typically requires the utilization of multi-party computation techniques to provide strong privacy guarantees by ensuring that an untrusted or curious aggregator cannot obtain isolated replies from parties involved in the training process, thereby preventing potential inference attacks. Until recently, it was thought that some of these secure aggregation techniques were sufficient to fully protect against inference attacks coming from a curious aggregator. However, recent research has demonstrated that a curious aggregator can successfully launch a disaggregation attack to learn information about model updates of a target party. This paper presents DeTrust-FL, an efficient privacy-preserving federated learning framework for addressing the lack of transparency that enables isolation attacks, such as disaggregation attacks, during secure aggregation by assuring that parties’ model updates are included in the aggregated model in a private and secure manner. DeTrust-FL proposes a decentralized trust consensus mechanism and incorporates a recently proposed decentralized functional encryption scheme in which all parties agree on a participation matrix before collaboratively generating decryption key fragments, thereby gaining control and trust over the secure aggregation process in a decentralized setting. Our experimental evaluation demonstrates that DeTrust-FL outperforms state-of-the-art FE-based secure multi-party aggregation solutions in terms of training time and reduces the volume of data transferred. In contrast to existing approaches, this is achieved without creating any trust dependency on external trusted entities.

Training complex neural network models using third-party cloud-based infrastructure among multiple data sources is a promising approach among existing machine learning solutions. However, privacy concerns of large-scale data collections and recent regulations have restricted the availability and use of privacy sensitive data in the third-party infrastructure. To address such privacy issues, a promising emerging approach is to train a neural network model over an encrypted dataset. Specifically, the model training process can be outsourced to a third party such as a cloud service that is backed by significant computing power, while the encrypted training data keeps the data confidential from the third party. Compared to training a traditional machine learning model over encrypted data, however, it is extremely challenging to train a deep neural network (DNN) model over encrypted data for two reasons: first, it requires large-scale computation over huge datasets; second, the existing solutions for computation over encrypted data, such as using homomorphic encryption, is inefficient. Further, for enhanced performance of a DNN model, we also need to use huge training datasets composed of data from multiple data sources that may not have pre-established trust relationships among each other. We propose a novel framework,NN-EMD, to train DNN overencrypted multiple datasetscollected from multiple sources. Toward this, we propose a set of secure computation protocols using hybrid functional encryption schemes. We evaluate our framework for performance with regards to the training time and model accuracy on the MNIST datasets. We show that compared to other existing frameworks, our proposedNN-EMDframework can significantly reduce the training time, while providing comparable model accuracy and privacy guarantees as well as supporting multiple data sources. Furthermore, the depth and complexity of neural networks do not affect the training time despite introducing a privacy-preservingNN-EMDsetting.

Advancements in distributed ledger technologies are driving the rise of blockchain-based social media platforms such as Steemit, where users interact with each other in similar ways as conventional social networks. These platforms are autonomously managed by users using decentralized consensus protocols in a cryptocurrency ecosystem. The deep integration of social networks and blockchains in these platforms provides potential for numerous cross-domain research studies that are of interest to both the research communities. However, it is challenging to process and analyze large volumes of raw Steemit data as it requires specialized skills in both software engineering and blockchain systems and involves substantial efforts in extracting and filtering various types of operations. To tackle this challenge, we collect over 38 million blocks generated in Steemit during a 45 month time period from 2016/03 to 2019/11 and extract ten key types of operations performed by the users. The results generate SteemOps, a new dataset that organizes more than 900 million operations from Steemit into three sub-datasets namely (i) social-network operation dataset (SOD), (ii) witness-election operation dataset (WOD) and (iii) value-transfer operation dataset (VOD). We describe the dataset schema and its usage in detail and outline possible future research studies using SteemOps. SteemOps is designed to facilitate future research aimed at providing deeper insights on emerging blockchain-based social media platforms.

Recent advances in information technologies have facilitated applications to generate, collect or process large amounts of sensitive personal data. Emerging cloud storage services provide a better paradigm to support the needs of such applications. Such cloud based solutions introduce additional security and privacy challenges when dealing with outsourced data including that of supporting fine-grained access control over such data stored in the cloud. In this paper, we propose an integrated, privacy-preserving user-centric attribute based access control framework to ensure the security and privacy of users' data outsourced and stored by a cloud service provider (CSP). The core component of the proposed framework is a novel privacy-preserving, revocable ciphertext policy attribute-based encryption (PR-CP-ABE) scheme. To support advanced access control features like write access on encrypted data and privacy-preserving access policy updates, we propose extended Path-ORAM access protocol that can also prevent privacy disclosure of access patterns. We also propose an integrated secure deduplication approach to improve the storage efficiency of CSPs while protecting data privacy. Finally, we evaluate the proposed framework and compare it with other existing solutions with regards to the security and performance issues.

Advancements in distributed ledger technologies are rapidly driving the rise of decentralized crowdsourcing systems on top of open smart contract platforms like Ethereum. While decentralized blockchain-based crowdsourcing provides numerous benefits compared to centralized solutions, current implementations of decentralized crowdsourcing suffer from fundamental scalability limitations by requiring all participants to pay a small transaction fee every time they interact with the blockchain. This increases the cost of using decentralized crowdsourcing solutions, resulting in a total payment that could be even higher than the price charged by centralized crowdsourcing platforms. This paper proposes a novel suite of protocols called NF-Crowd that resolves the scalability issue by reducing the lower bound of the total cost of a decentralized crowdsourcing project to O(1). NF-Crowd is a highly reliable solution for scaling decentralized crowdsourcing. We prove that as long as participants of a project powered by NF-Crowd are rational, the O(1) lower bound of cost could be reached regardless of the scale of the crowd. We also demonstrate that as long as at least one participant of a project powered by NF-Crowd is honest, the project cannot be aborted and the results are guaranteed to be correct. We design NF-Crowd protocols for a representative type of project named crowdsourcing contest with open community review (CC-OCR). We implement the protocols over the Ethereum official test network. Our results demonstrate that NF-Crowd protocols can reduce the cost of running a CC-OCR project to less than $2 regardless of the scale of the crowd, providing a significant cost benefit in adopting decentralized crowdsourcing solutions.

Recent advances in cryptographic approaches, such as Functional Encryption and Attribute-based Encryption and their variants, have shown significant promise for enabling public clouds to provide secure computation and storage services for users’ sensitive data. A crucial component of these approaches is a third-party authority (TPA) that must be trusted to set up public parameters, provide private key service, and so on. Components of deployed cryptographic mechanisms such as the certificate authorities (CAs) , which are the TPAs of the underlying PKI for the SSL/TLS protocol, have faced several types of attacks (e.g., stealthy targeted and censorship attacks), and certificate mis-issuance problems. Such practical challenges indicate that the successful deployment of newer emerging cryptographic schemes will also significantly depend on the trustworthiness of the TPAs. Furthermore, recently proposed decentralized TPA approaches that lower the threshold on the conditions required for an entity to become an authority can make the trust issue much worse. To address this issue, we propose an authority transparency framework to ensure the trustworthiness of TPAs of recent and emerging advanced cryptographic schemes. The framework includes a formal model and a secure logging -based approach to implement the framework. Further, to address the issues related to privacy, we also present a privacy-preserving authority transparency approach. We present security analysis and performance evaluation to show that authority transparency achieves the security and performance goals.

Emerging neural networks based machine learning techniques such as deep learning and its variants have shown tremendous potential in many application domains. However, they raise serious privacy concerns due to the risk of leakage of highly privacy-sensitive data when data collected from users is used to train neural network models to support predictive tasks. To tackle such serious privacy concerns, several privacy-preserving approaches have been proposed in the literature that use either secure multi-party computation (SMC) or homomorphic encryption (HE) as the underlying mechanisms. However, neither of these cryptographic approaches provides an efficient solution towards constructing a privacy-preserving machine learning model, as well as supporting both the training and inference phases. To tackle the above issue, we propose a CryptoNN framework that supports training a neural network model over encrypted data by using the emerging functional encryption scheme instead of SMC or HE. We also construct a functional encryption scheme for basic arithmetic computation to support the requirement of the proposed CryptoNN framework. We present performance evaluation and security analysis of the underlying crypto scheme and show through our experiments that CryptoNN achieves accuracy that is similar to those of the baseline neural network models on the MNIST dataset.

Recent advances in IT have enabled many applications that generate/collect huge amounts of personal data. While these advances have made many personalized applications such as personalized user-centric healthcare possible there are significant system maintenance cost related to data management, and security and privacy issues that need to be first addressed. Although cloud computing presents a new paradigm that helps maintaining users aggregated information distributed in different Internet enabled applications in one place, it also introduces new challenges in security and privacy. In this paper, we propose an integrated user-centric (or an organization-centric) privacy preserving attribute based access control approach to protect the security and privacy of a user's(or the organization's) data stored by a cloud service provider. The proposed approach includes a novel privacypreserving revocable ciphertext policy attribute-based encryption (PR-CP-ABE) scheme. We also propose an extended Path-ORAM protocol that addresses the access pattern privacy as users access the protected data on cloud. We present security and privacy analysis and compare the performance parameters with other existing approaches.