The digital transformation of educational systems has significantly optimized administrative workflows and enhanced the user experience for educators and learners. However, the accumulation of sensitive personal data on educational websites has made them prime targets for cyber threats. Despite growing awareness of these security challenges, the technical roots of vulnerabilities within such platforms remain insufficiently explored. To address this gap, we introduce LLM-EduAttackGraph, a specialized tool designed to assist in vulnerability detection by leveraging large language models (LLMs). Rather than serving as a fully automated monitoring system, LLM-EduAttackGraph operates as a human-in-the-loop assistant, combining expert knowledge with the analytical capabilities of LLMs to help identify potential penetration paths based on network fingerprint information. Using LLM-EduAttackGraph, we have so far identified 961 penetration vulnerabilities across educational websites in mainland China—a number that continues to grow as analysis progresses. These findings demonstrate the tool’s practical value in augmenting cybersecurity research and efforts. Our in-depth analysis of the discovered vulnerabilities reveals that limited developer experience and a heavy dependence on outsourced website development are key contributing factors. By shedding light on these root causes, our research offers actionable strategies and insights aimed at improving the cybersecurity posture of educational platforms and ensuring the sustainable development of online education. Furthermore, we have compared LLM-EduAttackGraph with several existing large model penetration tools to demonstrate the performance of LLM-EduAttackGraph. Such strengths include its low demand for hardware resources and having undergone empirical verification.

State-of-the-art asynchronous Byzantine fault-tolerant (BFT) protocols, such as HoneyBadgerBFT, BEAT, and Dumbo, have shown performance comparable to partially synchronous BFT protocols. This paper studies two practical directions in asynchronous BFT. First, while all these asynchronous BFT protocols assume optimal resilience with$3f+1$replicas (where$f$is an upper bound on the number of Byzantine replicas), it is interesting to ask whether more efficient protocols are possible upon changing the resilience level. Second, these recent BFT protocols evaluate their performance under failure-free scenarios. It is unclear if these protocols indeed perform well during failures and attacks. This work first studies asynchronous BFT with suboptimal resilience using$5f+1$and$7f+1$replicas. We present MiB, a novel and efficient asynchronous BFT framework using new distributed system constructions as building blocks. MiB consists of two main BFT instances and five more variants. As another contribution, we systematically design experiments for asynchronous BFT protocols with failures and evaluate their performance in various failure scenarios. We report interesting findings, showing that asynchronous BFT performs consistently well during different failure scenarios. In particular, via a five-continent deployment on Amazon EC2 using 140 replicas, we show that the MiB instances have lower latency and much higher throughput than their asynchronous BFT counterparts.

A key management service (KMS) is vital to modern mission-critical systems. At the core of KMS are the key generation process and the key refresh process. In this paper, we design and implement a purely asynchronous system for completely distributed KMS supporting traditional applications such as threshold cryptosystems and multiparty computation (MPC) as well as emerging blockchains and Web3 applications. In this system, we have built a number of new asynchronous distributed key generation (ADKG) protocols and their corresponding asynchronous distributed key refresh (ADKR) protocols. We have demonstrated that our ADKG and ADKR protocols in the standard model outperform existing ones of the same kind, while our protocols in the random oracle model (ROM) are more efficient than other protocols with small and medium-sized networks.

The advent of the Internet of Things (IoT) has brought forth an era of unprecedented connectivity, with an estimated 80 billion smart devices expected to be in operation by the end of 2025. These devices facilitate a multitude of smart applications, enhancing the quality of life and efficiency across various domains. Machine Learning (ML) serves as a crucial technology, not only for analyzing IoT-generated data but also for diverse applications within the IoT ecosystem. For instance, ML finds utility in IoT device recognition, anomaly detection, and even in uncovering malicious activities. This paper embarks on a comprehensive exploration of the security threats arising from ML’s integration into various facets of IoT, spanning various attack types including membership inference, adversarial evasion, reconstruction, property inference, model extraction, and poisoning attacks. Unlike previous studies, our work offers a holistic perspective, categorizing threats based on criteria such as adversary models, attack targets, and key security attributes (confidentiality, availability, and integrity). We delve into the underlying techniques of ML attacks in IoT environment, providing a critical evaluation of their mechanisms and impacts. Furthermore, our research thoroughly assesses 65 libraries, both author-contributed and third-party, evaluating their role in safeguarding model and data privacy. We emphasize the availability and usability of these libraries, aiming to arm the community with the necessary tools to bolster their defenses against the evolving threat landscape. Through our comprehensive review and analysis, this paper seeks to contribute to the ongoing discourse on ML-based IoT security, offering valuable insights and practical solutions to secure ML models and data in the rapidly expanding field of artificial intelligence in IoT.

Data-driven landscape across finance, government, and healthcare, the continuous generation of information demands robust solutions for secure storage, efficient dissemination, and fine-grained access control. Blockchain technology emerges as a significant tool, offering decentralized storage while upholding the tenets of data security and accessibility. However, on-chain and off-chain strategies are still confronted with issues such as untrusted off-chain data storage, absence of data ownership, limited access control policy for clients, and a deficiency in data privacy and auditability. To solve these challenges, we propose a permissioned blockchain-based privacy-preserving fine-grained access control on-chain and off-chain system, namely FACOS. We applied three fine-grained access control solutions and comprehensively analyzed them in different aspects, which provides an intuitive perspective for system designers and clients to choose the appropriate access control method for their systems. Compared to similar work that only stores encrypted data in centralized or non-fault-tolerant IPFS systems, we enhanced off-chain data storage security and robustness by utilizing a highly efficient and secure asynchronous Byzantine fault tolerance (BFT) protocol in the off-chain environment. As each of the clients needs to be verified and authorized before accessing the data, we involved the Trusted Execution Environment (TEE)-based solution to verify the credentials of clients. Additionally, our evaluation results demonstrated that our system (https://github.com/cliu717/AsynchronousStorage) offers better scalability and practicality than other state-of-the-art designs. We deployed our system on Alibaba Cloud and Tencent Cloud and conducted multiple evaluations. The results indicate that it takes about 2.79 seconds for a client to execute the protocol for uploading and about 0.96 seconds for downloading. Compared to other decentralized systems, our system exhibits efficient latency for both download and upload operations.

Distributed key generation (DKG) allows bootstrapping threshold cryptosystems without relying on a trusted party, nowadays enabling fully decentralized applications in blockchains and multiparty computation (MPC). While we have recently seen new advancements for asynchronous DKG (ADKG) protocols, their performance remains the bottleneck for many applications, with only one protocol being implemented (DYX+ ADKG, IEEE S&P 2022). DYX+ ADKG relies on the Decisional Composite Residuosity assumption (being expensive to instantiate) and the Decisional Diffie-Hellman assumption, incurring a high latency (more than 100s with a failure threshold of 16). Moreover, the security of DYX+ ADKG is based on the random oracle model (ROM) which takes hash function as an ideal function; assuming the existence of random oracle is a strong assumption, and up to now, we cannot find any theoretically-sound implementation. Furthermore, the ADKG protocol needs public key infrastructure (PKI) to support the trustworthiness of public keys. The strong models (ROM and PKI) further limit the applicability of DYX+ ADKG, as they would add extra and strong assumptions to underlying threshold cryptosystems. For instance, if the original threshold cryptosystem works in the standard model, then the system using DYX+ ADKG would need to use ROM and PKI. In this paper, we design and implement a modular ADKG protocol that offers improved efficiency and stronger security guarantees. We explore a novel and much more direct reduction from ADKG to the underlying blocks, reducing the computational overhead and communication rounds of ADKG in the normal case. Our protocol works for both the low-threshold and high-threshold scenarios, being secure under the standard assumption (the well-established discrete logarithm assumption only) in the standard model (no trusted setup, ROM, or PKI).

The impact of fog-assisted healthcare Internet of Things (H-IoT) system is immense. The smart H-IoT equipments can upload healthcare information to fog nodes with low latency and high mobility. To facilitate secure interactions among three parties, including smart H-IoT equipments, fog nodes, and a cloud server, over the public and insecure channels, a few authenticated key agreement (AKA) protocols are proposed. However, existing works are constructed based on expensive cryptographic primitives (e.g., bilinear pairing), which lead to high computation costs. Besides, the anonymity of H-IoT users is failed to be provided. To tackle these issues, an anonymous and lightweight three-party AKA protocol (ALAKAP) is proposed, which leverages an efficient cryptographic primitive (i.e., Chebyshev chaotic map operation) to generate a shared session key among three parties and achieve security (anonymity and other six properties) and efficiency simultaneously. It then formally proves the security of ALAKAP under the broadly accepted Burrows–Abadi–Needham (BAN) logic model and demonstrates how the proposed protocol satisfies the desired requirements in the fog-assisted H-IoT system. Finally, the performance of ALAKAP is validated by conducting the experiments on Amazon EC2 and Raspberry Pi. The results show that our work can achieve at least 44% higher improvement than the state-of-the-art works.

Adversarial attacks attempt to disrupt the training, retraining, and utilizing of artificial intelligence (AI) and machine learning models in large-scale distributed machine learning systems. This causes security risks on its prediction outcome. For example, attackers attempt to poison the model by either presenting inaccurate misrepresentative data or altering the models' parameters. In addition, Byzantine faults including software, hardware, network issues occur in distributed systems which also lead to a negative impact on the prediction outcome. In this paper, we propose a novel distributed training algorithm, partial synchronous stochastic gradient descent (ParSGD), which defends adversarial attacks and/or tolerates Byzantine faults. We demonstrate the effectiveness of our algorithm under three common adversarial attacks again the ML models and a Byzantine fault during the training phase. Our results show that using ParSGD, ML models can still produce accurate predictions as if it is not being attacked nor having failures at all when almost half of the nodes are being compromised or failed. We will report the experimental evaluations of ParSGD in comparison with other algorithms.

Asynchronous BFT protocols such as HoneyBadgerBFT and BEAT are inherently robust against timing, performance, and denial-of-service attacks. The protocols, however, achieve static security, where the adversary needs to choose the set of corrupted replicas before the execution of the protocol. The situation is in contrast to that of most of existing BFT protocols (e.g., PBFT) which achieve adaptive security, where the adversary can choose to corrupt replicas at any moment during the execution of the protocol. We present EPIC, a novel and efficient asynchronous BFT protocol with adaptive security. Via a five-continent deployment on Amazon EC2, we show that EPIC is slightly slower for small and medium-sized networks than the most efficient asynchronous BFT protocols with static security. We also find as the number of replicas is smaller than 46, EPIC's throughput is stable, achieving peak throughput of 8,000--12,500 tx/sec using t2.medium VMs. When the network size grows larger, EPIC is not as efficient as those with static security, with throughput of 4,000--6,300 tx/sec.

We present Chios, an intrusion-tolerant publish/subscribe system which protects against Byzantine failures. Chios is the first publish/subscribe system achieving decentralized confidentiality with fine-grained access control and strong publication order guarantees. This is in contrast to existing publish/subscribe systems achieving much weaker security and reliability properties. Chios is flexible and modular, consisting of four fully-fledged publish/subscribe configurations (each designed to meet different goals). We have deployed and evaluated our system on Amazon EC2. We compare Chios with various publish/subscribe systems. Chios is as efficient as an unreplicated, single-broker publish/subscribe implementation, only marginally slower than Kafka and Kafka with passive replication, and at least an order of magnitude faster than all Hyperledger Fabric modules and publish/subscribe systems using Fabric.