Blockchain Papers

Polaki Durga Prasad, Yelleti Vivek, Vadlamani Ravi

No abstract is available for this record.

Vishal N. Sulakhe, S. B. Goyal, Amit Gadekar, Manisha Wasnik · 6 authors

No abstract is available for this record.

Subhasis Thakur, John G. Breslin

Verification of a deep neural network is required as large DNN models are used in machine learning as a service procedure where the server providing a classification service may be insecure and provide invalid classifications. A verification of deep neural networks in a machine learning as a service paradigm requires verification of function evaluation for all functions of a DNN model given a specific input where the service provider and the server do not want to reveal the DNN model to the client. In this paper, we investigate the privacy-preserving verification problem of the DNN model with zero-knowledge proofs. We have developed a KGZ polynomial commitment scheme based on zero-knowledge proof for such DNN verification. We present an efficient DNN verification using KGZ zero-knowledge proof. We have developed a batch-processing algorithm that can significantly reduce the number of function evaluation verifications. We also prove that a malicious server may not manipulate the proposed verification protocol.

Fabio Severino, Andrea Canciani, Claudio Felicioli, Vincenzo Gervasi · 8 authors

In the field of Artificial Intelligence (AI), there is an increasing focus on enhancing trustworthiness especially in critical sectors such as in the management of civil infrastructure. This paper proposes the adoption of a framework based on Hybrid Distributed Ledger Technology (Hybrid-DLT) as a technological solution for improving trustworthiness. We detail three specific applications in the sector of critical infrastructure maintenance: Explainable AI (XAI) for risk classification, structural defects recognition, and real-time monitoring through IoT. The proposed approach employs tamper-resistant ledgers for tracking key processes such as dataset collection, model training, and inference generation, thereby ensuring non-repudiability for recorded actions and enabling auditability. We demonstrate how this strengthens the explainability mechanisms of AI models and enables the production of verifiable data lineage and certified inferences. Our framework can be applied to existing AI solutions, enhancing their trustworthiness.

Linlin Li, Chungen Xu, Pan Zhang

No abstract is available for this record.

Shengqiang Zeng, Hongwei Zhang, Jinsong Wang, Kai Shi

No abstract is available for this record.

Subhranil Das, Rashmi Kumari, Raghwendra Kishore Singh, Dev Rishi · 5 authors

Zero Knowledge Proofs (ZKPs) have emerged as transformative cryptographic primitives, enabling a wide variety of modern privacy-preserving applications across various domains. This paper presents substantial advancements in contemporary ZKPs, exploring the latest trends in ZKP schemes, novel applications, and scalable ZKP-based systems. We provide an in-depth analysis of state-of-the-art ZKP structures, including zk-SNARKs, zk-STARKs, and the more recent zk-Rollup technologies. We examine the unique properties and use cases of these techniques, highlighting their potential to enhance privacy, security, and trust in digital systems. Our research into zk-Rollups demonstrates significant improvements in transaction throughput and gas efficiency, paving the way for the extensive deployment of modern privacy-preserving solutions. Furthermore, we showcase several innovative applications of ZKPs, such as privacy-preserving decentralized finance (DeFi) protocols, anonymous credentials, and secure multi-party computation. These use cases illustrate the transformative potential of advanced ZKPs to improve privacy and security across a range of digital domains. To foster wider adoption of modern ZKPs, we have developed and opensourced a collection of advanced tools and libraries that simplify the implementation of ZKP-based solutions. We also offer practical guidance and best practices for developers and researchers working in this field, aiming to accelerate the development and real-world impact of modern zero-knowledge proof systems.

Vaibhav Ambhire, Tushar Nankani, Shobhit Mirjankar, Vivek Namaye · 5 authors

No abstract is available for this record.

Khizar Hameed, Faiqa Maqsood, Zhenfei Wang

No abstract is available for this record.

Andrea Pelosi, Claudio Felicioli, Andrea Canciani, Fabio Severino

While Artificial Intelligence (AI) is making significant strides in a variety of sectors, an exclusive focus on accuracy can overlook the critical aspect of trustworthiness, especially in contexts where it should be a primary concern. In this paper, we propose a novel framework for the development of trustworthy AI systems, leveraging Hybrid Distributed Ledger Technology (Hybrid DLT). We explore the concept of shifting from an accuracy-based paradigm to an approach where trustworthiness is an integral part of the design. Our framework facilitates collaboration between different entities across the data preparation, model training, and the classification phase of a supervised learning ML solution. It uses a shared ledger which offers a tamper-resistant audit log of every operation, ensuring non-repudiation and replicability. We discuss how employing our proposed framework leads to significantly enhanced trustworthiness in AI systems.

Boyi Zeng, Wang, Lizheng, Hu, Yuncong, Xu, Yi · 8 authors

Protecting the copyright of large language models (LLMs) has become crucial due to their resource-intensive training and accompanying carefully designed licenses. However, identifying the original base model of an LLM is challenging due to potential parameter alterations. In this study, we introduce HuRef, a human-readable fingerprint for LLMs that uniquely identifies the base model without interfering with training or exposing model parameters to the public. We first observe that the vector direction of LLM parameters remains stable after the model has converged during pretraining, with negligible perturbations through subsequent training steps, including continued pretraining, supervised fine-tuning, and RLHF, which makes it a sufficient condition to identify the base model. The necessity is validated by continuing to train an LLM with an extra term to drive away the model parameters' direction and the model becomes damaged. However, this direction is vulnerable to simple attacks like dimension permutation or matrix rotation, which significantly change it without affecting performance. To address this, leveraging the Transformer structure, we systematically analyze potential attacks and define three invariant terms that identify an LLM's base model. Due to the potential risk of information leakage, we cannot publish invariant terms directly. Instead, we map them to a Gaussian vector using an encoder, then convert it into a natural image using StyleGAN2, and finally publish the image. In our black-box setting, all fingerprinting steps are internally conducted by the LLMs owners. To ensure the published fingerprints are honestly generated, we introduced Zero-Knowledge Proof (ZKP). Experimental results across various LLMs demonstrate the effectiveness of our method. The code is available at https://github.com/LUMIA-Group/HuRef.

Umer Majeed, Sheikh Salman Hassan, Zhu Han, Choong Seon Hong

In the rapidly evolving landscape of Web3 and blockchain technologies, decentralized autonomous organizations (DAOs) have emerged as innovative structures that operate autonomously through blockchain and smart contracts, eliminating the need for centralized control. The federated learning (FL) process, akin to an information flow under structured transparency, involves local models (LMs) as inputs and the global model (GM) as the output for each global iteration. The lack of transparency and security in traditional FL systems can be attributed to the centralized validation of LMs and GM updates. In this paper, we propose DAO-FL, a smart contract-based framework that leverages the power of DAOs to address these FL challenges. DAO-FL introduces the concept of DAO Membership Tokens (DAOMTs) as a governance tool within a DAO. DAOMTs play a crucial role within the DAO, facilitating members’ enrollment and expulsion. Our framework incorporates a Validation-DAO for decentralized input verification (DIV) of the FL process, ensuring reliable and transparent validation of LMs. Additionally, DAO-FL employs a multi-signatures approach facilitated by an Orchestrator-DAO to achieve decentralized GM updates, and thus decentralized output verification (DOV) of the FL process. We present a comprehensive system architecture, detailed execution workflow, implementation specifications, and qualitative evaluation for DAO-FL. Evaluation under threat models highlights DAO-FL’s out-performance against traditional centralized-FL, effectively countering input and output attacks. DAO-FL excels in scenarios where DIV and DOV are crucial, offering enhanced transparency and trust. In conclusion, DAOFL provides a compelling solution for FL, reinforcing the integrity of the FL ecosystem through decentralized decision making and validation mechanisms.

Xiaohu Du, Xiao Chen, Jialun Cao, Ming Wen · 6 authors

Federated learning (FL) is an emerging machine learning paradigm that aims to address the problem of isolated data islands. To preserve privacy, FL allows machine learning models and deep neural networks to be trained from decentralized data kept privately at individual devices. FL has been increasingly adopted in missioncritical fields such as finance and healthcare. However, bugs in FL systems are inevitable and may result in catastrophic consequences such as financial loss, inappropriate medical decision, and violation of data privacy ordinance. While many recent studies were conducted to understand the bugs in machine learning systems, there is no existing study to characterize the bugs arising from the unique nature of FL systems. To fill the gap, we collected 395 real bugs from six popular FL frameworks (Tensorflow Federated, PySyft, FATE, Flower, PaddleFL, and Fedlearner) in GitHub and StackOverflow, and then manually analyzed their symptoms and impacts, prone stages, root causes, and fix strategies. Furthermore, we report a series of findings and actionable implications that can potentially facilitate the detection of FL bugs.

Yaman Jandali, Nojan Sheybani, Farinaz Koushanfar

With the rising use of aircrafts for operations ranging from disaster-relief to warfare, there is a growing risk of adversarial attacks. Malicious entities often only require the location of the aircraft for these attacks. Current satellite-aircraft communication and tracking protocols put aircrafts at risk if the satellite is compromised, due to computation being done in plaintext. In this work, we present \texttt{SPAM}, a private, secure, and accurate system that allows satellites to efficiently manage and maintain tracking angles for aircraft fleets without learning aircrafts' locations. \texttt{SPAM} is built upon multi-party computation and zero-knowledge proofs to guarantee privacy and high efficiency. While catered towards aircrafts, \texttt{SPAM}'s zero-knowledge fleet management can be easily extended to the IoT, with very little overhead.

Sunbeom So, Hakjoo Oh

We present SmartFix, a new technique for repairing vulnerable smart contracts. There is an urgent need to develop automatic bug-repair techniques for smart contracts, as smart contracts are safety-critical software and manual debugging is burdensome and error-prone. While several repair approaches have been proposed recently, they are unsatisfactory since no existing techniques can achieve high repairability, full automation, and safety guarantee at the same time, posing significant problems for practical use. SmartFix aims to address these shortcomings by using a “generate-and-verify” approach that iteratively enumerates candidate patches while validating their correctness by invoking a safety verifier. However, in this approach, a technical challenge arises as the search space is huge and the verification-based patch validation is expensive. To address this challenge, we present a novel technique for accelerating the generate-and-verify repair procedure using statistical models derived from the verifier’s feedback. Experimental results on real-world Ethereum smart contracts show that SmartFix is able to achieve a fix success rate of 94.8% for critical classes of vulnerabilities, far outperforming sGuard, the existing state-of-the-art technique whose success rate is 65.4%.

Kunsong Zhao, Zihao Li, Jianfeng Li, He Ye · 6 authors

Smart contracts play an increasingly important role in Ethereum platform. It provides various functions implementing numerous services, whose bytecode runs on Ethereum Virtual Machine. To use services by invoking corresponding functions, the callers need to know the function signatures. Moreover, such signatures provide crucial information for many downstream applications, e.g., identifying smart contracts, fuzzing, detecting vulnerabilities, etc. However, it is challenging to infer function signatures from the bytecode due to a lack of type information. Existing work solving this problem depended heavily on limited databases or hard-coded heuristic patterns. However, these approaches are hard to be adapted to semantic differences in distinct languages and various compiler versions when developing smart contracts. In this paper, we propose a novel framework DeepInfer that first leverages deep learning techniques to automatically infer function signatures and returns. The novelties of DeepInfer are: 1) DeepInfer lifts the bytecode into the Intermediate Representation (IR) to preserve code semantics; 2) DeepInfer extracts the type-related knowledge (e.g., critical data flows, constant values, and control flow graphs) from the IR to recover function signatures and returns. We conduct experiments on Solidity and Vyper smart contracts and the results show that DeepInfer performs faster and more accurate than existing tools, while being immune to changes in different languages and various compiler versions.

Yanli Wang, Sifei Sheng, Yanlin Wang

No abstract is available for this record.

Shobha Tyagi, Shobha Tyagi

The Zcash cryptocurrency is the first well-known application of zk-SNARKs in the blockchain. The role of Zk-SNARK is to provide privacy and confidentiality. As blockchain is incapable of providing privacy in the blockchain system, the researchers are banking at Zero Knowledge Proof protocols as the solution to the privacy problem. The Zero Knowledge Proof is a relatively new technique. Hence, currently, it comes with many risks and vulnerabilities. This paper mentions risks in cryptocurrency with Zero Knowledge Proof, primarily of Zcash. The discussed vulnerabilities are information leakage in transactions, trust risk, implementation vulnerability, and other security issues.

Sanjam Garg, Aarushi Goel, Somesh Jha, Saeed Mahloujifar · 7 authors

How can a model owner prove they trained their model according to the correct specification? More importantly, how can they do so while preserving the privacy of the underlying dataset and the final model? We study this problem and formulate the notion of zero-knowledge proof of training (zkPoT), which formalizes rigorous security guarantees that should be achieved by a privacy-preserving proof of training. While it is theoretically possible to design zkPoT for any model using generic zero-knowledge proof systems, this approach results in extremely unpractical proof generation times. Towards designing a practical solution, we propose the idea of combining techniques from MPC-in-the-head and zkSNARKs literature to strike an appropriate trade-off between proof size and proof computation time. We instantiate this idea and propose a concretely efficient, novel zkPoT protocol for logistic regression.

Alessandro Coglio, Eric McCarthy, Eric W. Smith

Zero-knowledge circuits are sets of equality constraints over arithmetic expressions interpreted in a prime field; they are used to encode computations in cryptographic zero-knowledge proofs. We make the following contributions to the problem of ensuring that a circuit correctly encodes a computation: a formal framework for circuit correctness; an ACL2 library for prime fields; an ACL2 model of the existing R1CS (Rank-1 Constraint Systems) formalism to represent circuits, along with ACL2 and Axe tools to verify circuits of this form; a novel PFCS (Prime Field Constraint Systems) formalism to represent hierarchically structured circuits, along with an ACL2 model of it and ACL2 tools to verify circuits of this form in a compositional and scalable way; verification of circuits, ranging from simple to complex; and discovery of bugs and optimizations in existing zero-knowledge systems.

Ehsan Toreini, Maryam Mehrnezhad, Aad van Moorsel

Abstract Providing trust in machine learning (ML) systems and their fairness is a socio-technical challenge, and while the use of ML continues to rise, there is lack of adequate processes and governance practices to assure their fairness. In this paper, we propose FaaS, a novel privacy-preserving, end-to-end verifiable solution, that audits the algorithmic fairness of ML systems. FaaS offers several features, which are absent from previous designs. The FAAS protocol is model-agnostic and independent of specific fairness metrics and can be utilised as a service by multiple stakeholders. FAAS uses zero knowledge proofs to assure the well-formedness of the cryptograms and provenance in the steps of the protocol. We implement a proof of concept of the FaaS architecture and protocol using off-the-shelf hardware, software, and datasets and run experiments to demonstrate its practical feasibility and to analyse its performance and scalability. Our experiments confirm that our proposed protocol is scalable to large-scale auditing scenarios (e.g. over 1000 participants) and secure against various attack vectors.

Keerthi Nelaturu, Eric Keilty, Andreas Veneris

Significant efforts have been dedicated to employing model-checking as a formal verification approach in the context of smart contracts. The utilization of these tools necessitates an in-depth knowledge on the part of the developer regarding both the programming language and the implementation of model-checking techniques. To provide accessibility to developers with basic language proficiency, we present a technique for developing a conversational application framework that can be seamlessly linked with any model-checking tool for the purpose of creating a smart contract. This architecture offers a robust and effective approach to the development of safe and dependable smart contracts. The utilization of natural language processing techniques in conjunction with neural networks is employed for this objective. Using this methodology, a prototype implementation for Move smart contracts has been created and is used with the VeriMove model-checking tool. Using the offered graphical user interface, we were able to successfully build, compile and test Move smart contracts across four different classes of smart contracts. This strategy effectively decreases the amount of time and effort needed for manual coding and debugging. In addition, the use of the VeriMove model-checking tool guarantees that the smart contracts produced are devoid of any potential vulnerabilities and flaws.

Zhibo Xing, Zijian Zhang, Ziang Zhang, Zhen Li · 11 authors

Over recent decades, machine learning has significantly advanced network communication, enabling improved decision-making, user behavior analysis, and fault detection. Simultaneously, the growth of communication networks has facilitated the efficient collection of large-scale training data. Traditional centralized machine learning, however, requires collecting data from users, raising significant concerns about privacy and security. Decentralized approaches, where participants exchange computation results instead of raw private data, mitigate these risks but introduce challenges related to trust and verifiability. A critical issue arises: How can one ensure the integrity and validity of computation results shared by other participants? Existing survey articles predominantly address security and privacy concerns in decentralized machine learning, whereas this survey uniquely highlights the emerging issue of verifiability. Recognizing the critical role of zero-knowledge proofs in ensuring verifiability, we present a comprehensive review of Zero-Knowledge Proof-based Verifiable Machine Learning (ZKP-VML). To clarify the research problem, we present a definition of ZKP-VML consisting of four algorithms and several key security properties. In addition, we provide an overview of the current research landscape by systematically organizing the research timeline and categorizing existing schemes based on their security properties. Furthermore, through an in-depth analysis of each existing scheme, we summarize their technical contributions and optimization strategies, aiming to uncover common design principles underlying ZKP-VML schemes. Building on the reviews and analysis presented, we identify current research challenges and suggest future research directions. To the best of our knowledge, this is the most comprehensive survey to date on verifiable decentralized machine learning and ZKP-VML.

Meng Wang, Ziheng Wang, Bin Yu, Kai Zhang

Attacks exploiting vulnerabilities in EOSIO smart contracts have caused serious economic losses. To detect these vulnerabilities, some approaches have been proposed, and concolic fuzzing is one of the most popular techniques among them. However, the existing concolic fuzzers have problems such as path explosion and adopting redundant constraint solving strategies, which reduce the detection efficiency. In order to alleviate these problems, we propose a demand-driven concolic fuzzing approach to discovering vulnerabilities in EOSIO smart contracts. In the approach, execution information is first collected to guide the execution of the system in a demand-driven manner. To improve the efficiency of vulnerability detection, we design a pruning strategy to eliminate the paths that are not relevant to the discovery of vulnerabilities and redundant paths to be explored. Meanwhile, an incremental constraint solving method is used to process only paths that can explore new branches. In addition, we also design a path prioritization method to preferentially explore paths which are more conducive to discovering vulnerabilities, so as to find vulnerabilities in smart contracts as early as possible. We have implemented our approach in a tool called WASAIUP and evaluated it on 3441 smart contracts. The experimental results show that WASAIUP improves the performance by 25.1% to 149.8% compared with the state-of-the-art tool WASAI in terms of efficiency, while maintaining high detection accuracy.