Yedi Zhang

Yedi Zhang

Auto-generated profile, based on publicly available information

Yedi Zhang

National University of Singapore, Singapore, Singapore

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 December 2022
Verified
Book Chapter
Closed access
PDF file
ZZZhe Zhao
Zhe Zhao
YZYedi Zhang
Yedi Zhang
GCGuangke Chen
Guangke Chen
FSFu Song
Fu Song
TCTaolue Chen
Taolue Chen
JLJiaxiang Liu
Jiaxiang Liu

27 April 2023 in ACM Transactions on Software Engineering and Methodology
Verified
Journal Article
Open access
YZYedi Zhang
Yedi Zhang
ZZZhe Zhao
Zhe Zhao
GCGuangke Chen
Guangke Chen
FSFu Song
Fu Song
TCTaolue Chen
Taolue Chen
As a new programming paradigm, neural-network-based machine learning has expanded its application to many real-world problems. Due to the black-box nature of neural networks, verifying and explaining their behavior are becoming increasingly important, especially when they are deployed in safety-critical applications. Existing verification work mostly focuses on qualitative verification, which asks whether there exists an input (in a specified region) for a neural network such that a property (e.g., local robustness) is violated. However, in many practical applications, such an (adversarial) input almost surely exists, which makes a qualitative answer less meaningful. In this work, we study a more interesting yet more challenging problem, i.e.,quantitativeverification of neural networks, which asks how often a property is satisfied or violated. We target binarized neural networks (BNNs), the 1-bit quantization of general neural networks. BNNs have attracted increasing attention in deep learning recently, as they can drastically reduce memory storage and execution time with bit-wise operations, which is crucial in recourse-constrained scenarios, e.g., embedded devices for Internet of Things. Toward quantitative verification of BNNs, we propose a novel algorithmic approach for encoding BNNs as Binary Decision Diagrams (BDDs), a widely studied model in formal verification and knowledge representation. By exploiting the internal structure of the BNNs, our encoding translates the input-output relation of blocks in BNNs to cardinality constraints, which are then encoded by BDDs. Based on the new BDD encoding, we develop a quantitative verification framework for BNNs where precise and comprehensive analysis of BNNs can be performed. To improve the scalability of BDD encoding, we also investigate parallelization strategies at various levels. We demonstrate applications of our framework by providing quantitative robustness verification and interpretability for BNNs. An extensive experimental evaluation confirms the effectiveness and efficiency of our approach.

9 April 2025 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
YZYedi Zhang
Yedi Zhang
LHLei Huang
Lei Huang
PGPengfei Gao
Pengfei Gao
FSFu Song
Fu Song
JSJun Sun
Jun Sun
JDJin Song Dong
Jin Song Dong
In the rapidly evolving landscape of neural network security, the resilience of neural networks against bit-flip attacks (i.e., an attacker maliciously flips an extremely small amount of bits within its parameter storage memory system to induce harmful behavior), has emerged as a relevant area of research. Existing studies suggest that quantization may serve as a viable defense against such attacks. Recognizing the documented susceptibility of real-valued neural networks to such attacks and the comparative robustness of quantized neural networks (QNNs), in this work, we introduce BFAVerifier, the first verification framework designed to formally verify the absence of bit-flip attacks against QNNs or to identify all vulnerable parameters in a sound and rigorous manner. BFAVerifier comprises two integral components: an abstraction-based method and an MILP-based method. Specifically, we first conduct a reachability analysis with respect to symbolic parameters that represent the potential bit-flip attacks, based on a novel abstract domain with a sound guarantee. If the reachability analysis fails to prove the resilience of such attacks, then we encode this verification problem into an equivalent MILP problem which can be solved by off-the-shelf solvers. Therefore, BFAVerifier is sound, complete, and reasonably efficient. We conduct extensive experiments, which demonstrate its effectiveness and efficiency across various activation functions, quantization bit-widths, and adversary capabilities.

16 October 2023 in Proceedings of the ACM on Programming Languages
Verified
Journal Article
Open access
PGPengfei Gao
Pengfei Gao
YZYedi Zhang
Yedi Zhang
FSFu Song
Fu Song
TCTaolue Chen
Taolue Chen
FSFrancois-Xavier Standaert
Francois-Xavier Standaert
Masking is one of the most effective countermeasures for securely implementing cryptographic algorithms against power side-channel attacks, the design of which however turns out to be intricate and error-prone. While techniques have been proposed to rigorously verify implementations of cryptographic algorithms, currently they are limited in scalability. To address this issue, compositional approaches have been investigated, but insofar they fail to prove the security of recent efficient implementations. To fill this gap, we propose a novel compositional verification approach. In particular, we introduce two new language-level security notions based on which we propose composition strategies and verification algorithms. Our approach is able to prove efficient implementations, which cannot be done by prior compositional approaches. We implement our approach as a tool CONVINCE and conduct extensive experiments to confirm its efficacy. We also use CONVINCE to further explore the design space of the AES Sbox with least refreshing by replacing its implementation for finite-field multiplication with more efficient counterparts. We automatically prove leakage-freeness of these new versions. As a result, we can effectively reduce 1,600 randomness and 3,200 XOR-operations of the state-of-the-art AES implementation.

27 October 2024
Verified
Conference Paper
Open access
JDJinhao Dong
Jinhao Dong
JSJun Sun
Jun Sun
YLYun Lin
Yun Lin
YZYedi Zhang
Yedi Zhang
MMMurong Ma
Murong Ma
DHDan Hao
Dan Hao
Collaborative software development significantly enhances development productivity by enabling multiple contributors to work concurrently on different branches. Despite these advantages, such collaboration often increases the likelihood of causing conflicts. Resolving these conflicts brings huge challenges, primarily due to the necessity of comprehending the differences between conflicting versions. Researchers have explored various automatic conflict resolution techniques, including unstructured, structured, and learning-based approaches. However, these techniques are mostly heuristic-based or black-box in nature, which means they do not attempt to solve the root cause of the conflicts, i.e., the existence of different program behaviors exhibited by the conflicting versions. In this work, we propose sMerge, a novel conflict resolution approach based on the semantics of program behaviors. We first give the formal definition of the merge conflict problem as well as the specific conditions under which conflicts happen and the criteria employed to select certain version as the resolution. Based on the definition, we propose to resolve the conflicts from the perspective of program behaviors. In particular, we argue that the key to resolving conflicts is identifying different program behaviors, and thus can be solved through targeted test generation. We conduct an extensive evaluation of sMerge using a comprehensive dataset of conflicts sourced from various projects. Our results show that sMerge can effectively solve the merge problem by employing different test generation techniques, including search-based, GPT-based, and manual testing. We remark that sMerge provides a way to understand the program behavior differences through testing, which not only allows us to solve the merge problem soundly but also enables the detection of incorrect ground truths provided by developers, thereby enhancing the reliability of the merge process.

12 March 2021 in arXiv
Verified
Preprint
Open access
PDF file
YZYedi Zhang
Yedi Zhang
ZZZhe Zhao
Zhe Zhao
GCGuangke Chen
Guangke Chen
FSFu Song
Fu Song
TCTaolue Chen
Taolue Chen
Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications. In this paper, we study verification problems for Binarized Neural Networks (BNNs), the 1-bit quantization of general real-numbered neural networks. Our approach is to encode BNNs into Binary Decision Diagrams (BDDs), which is done by exploiting the internal structure of the BNNs. In particular, we translate the input-output relation of blocks in BNNs to cardinality constraints which are then encoded by BDDs. Based on the encoding, we develop a quantitative verification framework for BNNs where precise and comprehensive analysis of BNNs can be performed. We demonstrate the application of our framework by providing quantitative robustness analysis and interpretability for BNNs. We implement a prototype tool BDD4BNN and carry out extensive experiments which confirm the effectiveness and efficiency of our approach.