Federated learning allows several clients to train one machine learning model jointly without sharing private data, providing privacy protection. However, traditional federated learning is vulnerable to poisoning attacks, which can not only decrease the model performance, but also implant malicious backdoors. In addition, direct submission of local model parameters can also lead to the privacy leakage of the training dataset. In this paper, we aim to build a privacy-preserving and Byzantine-robust federated learning scheme to provide an environment with no vandalism (NoV) against attacks from malicious participants. Specifically, we construct a model filter for poisoned local models, protecting the global model from data and model poisoning attacks. This model filter combines zero-knowledge proofs to provide further privacy protection. Then, we adopt secret sharing to provide verifiable secure aggregation, removing malicious clients that disrupting the aggregation process. Our formal analysis proves that NoV can protect data privacy and weed out Byzantine attackers. Our experiments illustrate that NoV can effectively address data and model poisoning attacks, including PGD, and outperforms other related schemes.
Green and low-carbon development is an important part of global sustainable development. Green power trading provides strong support and assurance for promoting green and low-carbon development. Due to the long cycle of green power data chains and their susceptibility to malicious tampering, the integrity and traceability of data are difficult to guarantee. Therefore, this paper first proposes a security provenance model with enhanced relations based on the core structure of PROV and blockchain technology, which can securely capture provenance records, use the transfer time and number of transactions between various links in the traceability network as reasoning clues, realize the correlation tracing of the green electricity transfer process. Under the model, a traceability mechanism of green electricity is designed based on smart contracts. Trustworthy green electricity data collection is achieved through data filling and data verification techniques. Traceability query technique is adopted to achieve trustworthy traceability of green electricity. And the effectiveness of the proposed solution is demonstrated through simulation experiments.
Open access
Blockchain Technology Applications and Security
Innovative Microfluidic and Catalytic Techniques Innovation
The rapid advancement and integration of Artificial Intelligence (AI) across critical sectors — including healthcare, finance, defense, and infrastructure — have exposed an often-overlooked risk: vulnerabilities within the AI supply chain. This research examines the security challenges and potential threats affecting AI model development and deployment, focusing on adversarial attacks, data poisoning, model theft, and compromised third-party components. By dissecting the AI supply chain into its core stages — data sourcing, model training, deployment, and maintenance — this study identifies key entry points for malicious actors. The paper proposes a multi-layered security framework combining blockchain-based data provenance, federated learning for decentralized model training, and zero-trust architecture to ensure secure deployment. Additionally, it explores how adversarial training, model watermarking, and real-time anomaly detection can mitigate risks without sacrificing model performance. Case studies of high-profile AI breaches are analyzed to demonstrate the consequences of unsecured pipelines, emphasizing the urgency of securing AI systems.
Open access
Ethics and Social Impacts of AI
Artificial Intelligence in Healthcare and Education
Gopinath Ganapathy, Sujatha Jamuna Anand, M. Jayaprakash, S. Lakshmi · 6 authors
The wide use of sensors in healthcare applications has made it necessary to have secure communication in healthcare Internet of Things (IoT) networks. The sensor data is sensitive, and can contain extremely confidential information such as medical diagnosis, clinical records, vital signs and health data of patients. The emergence of blockchain as a technology ensures consensus and trust among systems, and is now considered to be a new trend used to achieve high scalability, data integrity and privacy. Federated learning is a new technology based on distributed learning that exploits the concept of trust. In federated learning, each user builds an individual distributed model to help a central server that is accessible only to a trusted user group. This paper harnesses the potential of these approaches and proposes an attack detection model to discern normal user behaviours from that of adversaries in a IoT network. This model is called the Blockchain enabled Federated Learning model for secured communication in healthcare IoT (BFL-hIoT), to secure data in healthcare IoT networks. This model is trained and tested on a standard dataset and demonstrates the highest classification accuracy of 97.16% for normal, 0.9546 for backdoors, 0.9618 for XSS etc., outperforming other blockchain and deep learning models.
Boyuan Feng, Zheng Wang, Yuke Wang, Shu Yang · 5 authors
Zero knowledge Neural Networks draw increasing attention for guaranteeing computation integrity and privacy of neural networks (NNs) based on zero-knowledge Succinct Non-interactive ARgument of Knowledge (zkSNARK) security scheme. However, the performance of zkSNARK NNs is far from optimal due to the million-scale circuit computation with heavy scalar-level dependency. In this paper, we propose a type-based optimizing framework for efficient zero-knowledge NN inference, namely ZENO (ZEro knowledge Neural network Optimizer). We first introduce ZENO language construct to maintain high-level semantics and the type information (e.g., privacy and tensor) for allowing more aggressive optimizations. We then propose privacy-type driven and tensor-type driven optimizations to further optimize the generated zkSNARK circuit. Finally, we design a set of NN-centric system optimizations to further accelerate zkSNARK NNs. Experimental results show that ZENO achieves up to 8.5× end-to-end speedup than state-of-the-art zkSNARK NNs. We reduce proof time for VGG16 from 6 minutes to 48 seconds, which makes zkSNARK NNs practical.
Yepeng Ding, Arthur Gervais, Roger Wattenhofer, Hiroyuki Satō
Decentralized finance (DeFi) is revolutionizing the traditional centralized finance paradigm with its attractive features such as high availability, transparency, and tamper-proofing. However, attacks targeting DeFi services have severely damaged the DeFi market, as evidenced by our investigation of 80 real-world DeFi incidents from 2017 to 2022. Existing methods, based on symbolic execution, model checking, semantic analysis, and fuzzing, fall short in identifying the most DeFi vulnerability types. To address the deficiency, we propose Context-Sensitive Concolic Verification (CSCV), a method of automating the DeFi vulnerability finding based on user-defined properties formulated in temporal logic. CSCV builds and optimizes contexts to guide verification processes that dynamically construct context-carrying transition systems in tandem with concolic executions. Furthermore, we demonstrate the effectiveness of CSCV through experiments on real-world DeFi services and qualitative comparison. The experiment results show that our CSCV prototype successfully detects 76.25% of the vulnerabilities from the investigated incidents with an average time of 253.06 seconds.
Symbolic execution is a frequently used method for vulnerability detection in smart contracts. However, existing tools face limitations with the constraint solving and may cause the "path explosion" problem. This costs too much time and may lead to False-Negative (FN) of detection results. In this work, we propose ParSE, a novel approach that leverages Parallel and Simplified symbolic Execution to improve both detection efficiency and the number of True-Positive (TP). We inject ParSE into two widely used symbolic execution tools, Oyente and Mythril, for detecting vulnerabilities in smart contracts. Experimental results show that ParSE accelerates to 9.33x and 5.30x for Oyente and Mythril, respectively. Moreover, tools based on ParSE improve the detection number of TP.
Most concurrent blockchain systems rely heavily on the Proof-of-Work (PoW) or Proof-of-Stake (PoS) mechanisms for decentralized consensus and security assurance. However, the substantial energy expenditure stemming from computationally intensive yet meaningless tasks has raised considerable concerns surrounding traditional PoW approaches, The PoS mechanism, while free of energy consumption, is subject to security and economic issues. Addressing these issues, the paradigm of Proof-of-Useful-Work (PoUW) seeks to employ challenges of practical significance as PoW, thereby imbuing energy consumption with tangible value. While previous efforts in Proof of Learning (PoL) explored the utilization of deep learning model training SGD tasks as PoUW challenges, recent research has revealed its vulnerabilities to adversarial attacks and the theoretical hardness in crafting a byzantine-secure PoL mechanism. In this paper, we introduce the concept of incentive-security that incentivizes rational provers to behave honestly for their best interest, bypassing the existing hardness to design a PoL mechanism with computational efficiency, a provable incentive-security guarantee and controllable difficulty. Particularly, our work is secure against two attacks, and also improves the computational overhead from $Θ(1)$ to $O(\frac{\log E}{E})$. Furthermore, while most recent research assumes trusted problem providers and verifiers, our design also guarantees frontend incentive-security even when problem providers are untrusted, and verifier incentive-security that bypasses the Verifier's Dilemma. By incorporating ML training into blockchain consensus mechanisms with provable guarantees, our research not only proposes an eco-friendly solution to blockchain systems, but also provides a proposal for a completely decentralized computing power market in the new AI age.
As an essential component in Ethereum and other blockchains, token assets have been interacted with by diverse smart contracts. Effective permission policies of smart contracts must prevent token assets from being manipulated by unauthorized adversaries. Recent efforts have studied the accessibility of privileged functions or state variables to unauthorized users. However, little attention is paid to how publicly accessible functions of smart contracts can be manipulated by adversaries to steal users' digital assets. This attack is mainly caused by the permission re-delegation (PRD) vulnerability. In this work, we propose PrettySmart, a bytecode-level Permission re-delegation vulnerability detector for Smart contracts. Our study begins with an empirical study on 0.43 million open-source smart contracts, revealing that five types of widely-used permission constraints dominate 98% of the studied contracts. Accordingly, we propose a mechanism to infer these permission constraints, as well as an algorithm to identify constraints that can be bypassed by unauthorized adversaries. Based on the identification of permission constraints, we propose to detect whether adversaries could manipulate the privileged token management functionalities of smart contracts. The experimental results on real-world datasets demonstrate the effectiveness of the proposed PrettySmart, which achieves the highest precision score and detects 118 new PRD vulnerabilities.
Blockchain is a decentralized and distributed ledger system that records and verifies transactions across a network of computers and ensures transparency, immutability, and trustworthiness. Smart contracts are programs or protocols embedded into the distributed ledgers and are used to automate agreements between parties of a blockchain. Smart contracts are vulnerable to attacks due to their immutable and public nature, thus, it is important to guarantee the correctness of contracts already at design-time in order to avoid catastrophic events and huge loss of money.
The rapid proliferation of AI-generated “deepfake” images, audio, and video is eroding public trust in digital media and amplifying risks to elections, markets, journalism, and personal safety. While AI detection models have improved, they face an adversarial “cat-and-mouse” problem and often struggle to generalize across manipulation methods and compression regimes. This manuscript proposes and analyzes a hybrid, end-to-end approach that couples upstream provenance and authenticity signals—anchored via open standards (e.g., C2PA Content Credentials) and decentralized ledgers—with downstream AI detection and moderation. The pipeline captures and signs media at source; binds verifiable, tamper-evident metadata; anchors cryptographic hashes on a public or consortium blockchain; stores originals off-chain with content addressing (e.g., IPFS/Filecoin); and fuses these trust signals with model-based detectors and policy engines at distribution edges. We situate the proposal within current regulation (e.g., EU AI Act transparency duties) and state-of-the-art methods (e.g., watermarking such as SynthID, Stable Signature, and Tree-Ring; deepfake detectors trained on DFDC and FaceForensics++), highlighting both strengths and known attack vectors against watermarking that motivate layered defenses. A simulation-based evaluation illustrates that combining provenance signals with video-level transformer detectors can raise F1 from 0.85 to 0.92 while cutting false positives by ~41% in a balanced test set, primarily by rejecting credential-mismatched or hash-divergent media before expensive model inference. We further discuss privacy-preserving verification using W3C Verifiable Credentials (VC 2.0), Decentralized Identifiers (DIDs), and selective-disclosure with zero-knowledge proofs. The findings make a practical case for “trust by design” built on open standards, decentralized integrity proofs, and robust AI detection, implemented as a policy-aware defense-in-depth stack for platforms and newsrooms.
The metaverse, envisioned as the next digital frontier for avatar-based virtual interaction, involves high-performance models. In this dynamic environment, users' tasks frequently shift, requiring fast model personalization despite limited data. This evolution consumes extensive resources and requires vast data volumes. To address this, meta-learning emerges as an invaluable tool for metaverse users, with federated meta-learning (FML), offering even more tailored solutions owing to its adaptive capabilities. However, the metaverse is characterized by users heterogeneity with diverse data structures, varied tasks, and uneven sample sizes, potentially undermining global training outcomes due to statistical difference. Given this, an urgent need arises for smart coalition formation that accounts for these disparities. This paper introduces a dual game-theoretic framework for metaverse services involving meta-learners as workers to manage FML. A blockchain-based cooperative coalition formation game is crafted, grounded on a reputation metric, user similarity, and incentives. We also introduce a novel reputation system based on users' historical contributions and potential contributions to present tasks, leveraging correlations between past and new tasks. Finally, a Stackelberg game-based incentive mechanism is presented to attract reliable workers to participate in meta-learning, minimizing users' energy costs, increasing payoffs, boosting FML efficacy, and improving metaverse utility. Results show that our dual game framework outperforms best-effort, random, and non-uniform clustering schemes - improving training performance by up to 10%, cutting completion times by as much as 30%, enhancing metaverse utility by more than 25%, and offering up to 5% boost in training efficiency over non-blockchain systems, effectively countering misbehaving users.
Ensuring strict adherence to security during the phases of Android app development is essential, primarily due to the prevalent issue of apps being released without adequate security measures in place. While a few automated tools are employed to reduce potential vulnerabilities during development, their effectiveness in detecting vulnerabilities may fall short. To address this, “Defendroid”, a blockchain-based federated neural network enhanced with Explainable Artificial Intelligence (XAI) is introduced in this work. Trained on the LVDAndro dataset, the vanilla neural network model achieves a 96% accuracy and 0.96 F1-Score in binary classification for vulnerability detection. Additionally, in multi-class classification, the model accurately identifies Common Weakness Enumeration (CWE) categories with a 93% accuracy and 0.91 F1-Score. In a move to foster collaboration and model improvement, the model has been deployed within a blockchain-based federated environment. This environment enables community-driven collaborative training and enhancements in partnership with other clients. The extended model demonstrates improved accuracy of 96% and F1-Score of 0.96 in both binary and multi-class classifications. The use of XAI plays a pivotal role in presenting vulnerability detection results to developers, offering prediction probabilities for each word within the code. This model has been integrated into an Application Programming Interface (API) as the backend and further incorporated into Android Studio as a plugin, facilitating real-time vulnerability detection. Notably, Defendroid exhibits high efficiency, delivering prediction probabilities for a single code line in an average processing time of a mere 300 ms. The weight-sharing transparency in the blockchain-driven federated model enhances trust and traceability, fostering community engagement while preserving source code privacy and contributing to accuracy improvement.
Smart contracts, as a key component of blockchain technology, play a crucial role in ensuring the automation of transactions and adherence to protocol rules. However, smart contracts are susceptible to security vulnerabilities, which, if exploited, can lead to significant asset losses. This study explores the potential of enhancing smart contract security audits using the GPT-4 model. We utilized a dataset of 35 smart contracts from the SolidiFI-benchmark vulnerability library, containing 732 vulnerabilities, and compared it with five other vulnerability detection tools to evaluate GPT-4's ability to identify seven common types of vulnerabilities. Moreover, we assessed GPT-4's performance in code parsing and vulnerability capture by simulating a professional auditor's auditing process using CoT(Chain of Thought) prompts based on the audit reports of eight groups of smart contracts. We also evaluated GPT-4's ability to write Solidity Proof of Concepts (PoCs). Through experimentation, we found that GPT-4 performed poorly in detecting smart contract vulnerabilities, with a high Precision of 96.6%, but a low Recall of 37.8%, and an F1-score of 41.1%, indicating a tendency to miss vulnerabilities during detection. Meanwhile, it demonstrated good contract code parsing capabilities, with an average comprehensive score of 6.5, capable of identifying the background information and functional relationships of smart contracts; in 60% of the cases, it could write usable PoCs, suggesting GPT-4 has significant potential application in PoC writing. These experimental results indicate that GPT-4 lacks the ability to detect smart contract vulnerabilities effectively, but its performance in contract code parsing and PoC writing demonstrates its significant potential as an auxiliary tool in enhancing the efficiency and effectiveness of smart contract security audits.
Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh, Kamalika Chaudhuri
Machine learning models are increasingly used in societal applications, yet legal and privacy concerns demand that they very often be kept confidential. Consequently, there is a growing distrust about the fairness properties of these models in the minds of consumers, who are often at the receiving end of model predictions. To this end, we propose \name -- a system that uses Zero-Knowledge Proofs (a cryptographic primitive) to publicly verify the fairness of a model, while maintaining confidentiality. We also propose a fairness certification algorithm for fully-connected neural networks which is befitting to ZKPs and is used in this system. We implement \name in Gnark and demonstrate empirically that our system is practically feasible. Code is available at https://github.com/infinite-pursuits/FairProof.
Haya R. Hasan, Khaled Salah, Raja Jayaraman, Ibrar Yaqoob · 5 authors
The metaverse has gained immense popularity in recent years. However, the widespread adoption of this immersive virtual environment faces a substantial challenge from deepfake technology. The proliferation of deepfakes poses a significant risk as it enables the dissemination of misinformation and manipulated digital media. In this paper, we propose a blockchain and Non-Fungible Tokens (NFTs) based solution to combat the threats associated with deepfakes. Our proposed solution is applicable to various types of digital media found on the internet, social media platforms, and within the metaverse. We incorporate decentralized off-chain storage to ensure the security and integrity of digital media. This leads to preserving both the digital media and associated NFT metadata in a secure manner. We leverage the intrinsic features of blockchain, such as tamper-proof logs and data provenance, to enable users to verify the authenticity of digital media. We introduce a decentralized reputation system that employs equations, trust factors, and trust badges. Through this system, digital creators are incentivized with trust badges based on their trust factor values, which enhances the overall credibility of the content. We present the cost and security analyses as well as provide a comparative evaluation against existing solutions. We make our smart contract code publicly available on GitHub.
Bianca-Mihaela Ganescu, Jonathan Passerat‐Palmbach
Generative AI, exemplified by models like transformers, has opened up new possibilities in various domains but also raised concerns about fairness, transparency and reliability, especially in fields like medicine and law. This paper emphasizes the urgency of ensuring fairness and quality in these domains through generative AI. It explores using cryptographic techniques, particularly Zero-Knowledge Proofs (ZKPs), to address concerns regarding performance fairness and accuracy while protecting model privacy. Applying ZKPs to Machine Learning models, known as ZKML (Zero-Knowledge Machine Learning), enables independent validation of AI-generated content without revealing sensitive model information, promoting transparency and trust. ZKML enhances AI fairness by providing cryptographic audit trails for model predictions and ensuring uniform performance across users. We introduce snarkGPT, a practical ZKML implementation for transformers, to empower users to verify output accuracy and quality while preserving model privacy. We present a series of empirical results studying snarkGPT's scalability and performance to assess the feasibility and challenges of adopting a ZKML-powered approach to capture quality and performance fairness problems in generative AI models.
Given the growing importance of smart contracts in various applications, ensuring their security and reliability is critical. Fuzzing, an effective vulnerability detection technique, has recently been widely applied to smart contracts. Despite numerous studies, a systematic investigation of smart contract fuzzing techniques remains lacking. In this paper, we fill this gap by: 1) providing a comprehensive review of current research in contract fuzzing, and 2) conducting an in-depth empirical study to evaluate state-of-the-art contract fuzzers' usability. To guarantee a fair evaluation, we employ a carefully-labeled benchmark and introduce a set of pragmatic performance metrics, evaluating fuzzers from five complementary perspectives. Based on our findings, we provide direction for the future research and development of contract fuzzers.
As blockchain platforms grow exponentially, millions of lines of smart contract code are being deployed to manage extensive digital assets. However, vulnerabilities in this mission-critical code have led to significant exploitations and asset losses. Thorough automated security analysis of smart contracts is thus imperative. This paper introduces LLM4Fuzz to optimize automated smart contract security analysis by leveraging large language models (LLMs) to intelligently guide and prioritize fuzzing campaigns. While traditional fuzzing suffers from low efficiency in exploring the vast state space, LLM4Fuzz employs LLMs to direct fuzzers towards high-value code regions and input sequences more likely to trigger vulnerabilities. Additionally, LLM4Fuzz can leverage LLMs to guide fuzzers based on user-defined invariants, reducing blind exploration overhead. Evaluations of LLM4Fuzz on real-world DeFi projects show substantial gains in efficiency, coverage, and vulnerability detection compared to baseline fuzzing. LLM4Fuzz also uncovered five critical vulnerabilities that can lead to a loss of more than $247k.
The exploitation of smart contract vulnerabilities in Decentralized Finance (DeFi) has resulted in financial losses exceeding 3 billion US dollars. Existing defense mechanisms primarily focus on detecting and reacting to adversarial transactions executed by attackers that target victim contracts. However, with the emergence of private transaction pools where transactions are sent directly to miners without first appearing in public mempools, current detection tools face significant challenges in identifying attack activities effectively. Based on the fact that most attack logic rely on deploying intermediate smart contracts as supporting components to the exploitation of victim contracts, novel detection methods have been proposed that focus on identifying these adversarial contracts instead of adversarial transactions. However, previous state-of-the-art approaches in this direction have failed to produce results satisfactory enough for real-world deployment. In this paper, we propose LookAhead, a new framework for detecting DeFi attacks via unveiling adversarial contracts. LookAhead leverages common attack patterns, code semantics and intrinsic characteristics found in adversarial smart contracts to train Machine Learning (ML)-based classifiers that can effectively distinguish adversarial contracts from benign ones and make timely predictions of different types of potential attacks. Experiments on our labeled datasets show that LookAhead achieves an F1-score as high as 0.8966, which represents an improvement of over 44.4% compared to the previous state-of-the-art solution, with a False Positive Rate (FPR) at only 0.16%.
As a decentralized network infrastructure, the data sent to the blockchain are public and temper-evident. The cover of massive normal transactions in a blockchain network is ideal for constructing a stable and reliable covert channel to achieve one-to-many group covert communication. Existing blockchain-based covert communication schemes face challenges in balancing concealment, embedding rate and filtering efficiency, making them unsuitable for direct extension to group scenarios. Adopting a key-leakage scheme can increase the channel capacity while maintaining high concealment from external adversaries. However, it will also expose more knowledge to the receiver. A malicious receiver has the ability to steal a sender’s identity or replay historical transactions to control the entire channel. In this paper, we define the capabilities of malicious receivers in blockchain-based group covert communication scenarios and propose a group covert communication scheme resistant to transaction forgery attacks. Theoretical analysis and experiments prove that our covert transactions do not have any transaction correlativity, ensuring the unique authenticity of the sender’s identity while maintaining supreme concealment compared with the existing schemes. The precision and recall of machine learning detection results can reach 0.57–0.62 (0.5 is the ideal value).
Open access
Internet Traffic Analysis and Secure E-voting
Adversarial Robustness in Machine Learning
Advanced Steganography and Watermarking Techniques
Smart contracts are computer programs that run on a blockchain. As the functions implemented by smart contracts become increasingly complex, the number of cross-contract interactions within them also rises. Consequently, the combinatorial explosion of transaction sequences poses a significant challenge for smart contract security vulnerability detection. Existing static analysis-based methods for detecting cross-contract vulnerabilities suffer from high false-positive rates and cannot generate test cases, while fuzz testing-based methods exhibit low code coverage and may not accurately detect security vulnerabilities. The goal of this paper is to address the above limitations and efficiently detect cross-contract vulnerabilities. To achieve this goal, we present CrossFuzz, a fuzz testing-based method for detecting cross-contract vulnerabilities. First, CrossFuzz generates parameters of constructors by tracing data propagation paths. Then, it collects inter-contract data flow information. Finally, CrossFuzz optimizes mutation strategies for transaction sequences based on inter-contract data flow information to improve the performance of fuzz testing. We implemented CrossFuzz, which is an extension of ConFuzzius, and conducted experiments on a real-world dataset containing 396 smart contracts. The results show that CrossFuzz outperforms xFuzz, a fuzz testing-based tool optimized for cross-contract vulnerability detection, with a 10.58% increase in bytecode coverage. Furthermore, CrossFuzz detects 1.82 times more security vulnerabilities than ConFuzzius. Our method utilizes data flow information to optimize mutation strategies. It significantly improves the efficiency of fuzz testing for detecting cross-contract vulnerabilities.
As machine learning permeates sensitive domains such as healthcare, finance, and government, protecting individual privacy while leveraging large-scale data remains a paramount challenge. Privacy-Preserving Machine Learning (PPML) combines cryptographic techniques, decentralized training paradigms, and data governance policies to enable secure and compliant model development. This paper provides a comprehensive survey of fundamental PPML methods differential privacy, federated learning, homomorphic encryption and examines key data governance frameworks underpinning ethical AI adoption. We analyze technical trade-offs, including privacy-utility balance, scalability, and adversarial resilience. Finally, ongoing research directions and policy implications are discussed, emphasizing interdisciplinary collaboration for trustworthy AI deployment.