arXiv subjects

Liyi Zhou

Publications and source records attributed to Liyi Zhou.

At least 19 recordsLinked to original sources

arXiv2026

Principal nonsingularity of the Fourier matrices of orders $70$ and $143$

We give computer-assisted proofs that every principal minor of each of the $70\times70$ and $143\times143$ Fourier matrices is nonzero. A lifting theorem of Caragea, Lee, Malikiosis, and Pfander reduces the two assertions to the nonvanishing of all principal minors of the Fourier matrix of order $10$ in characteristic $7$, and of order $11$ in characteristic $13$, respectively. We realize primitive roots in $\mathbb F_{7^4}$ and $\mathbb F_{13^{10}}$ and evaluate all $2^{10}$ and $2^{11}$ principal determinants by exact, division-free arithmetic. None vanishes. The lifting theorem in fact yields the stronger conclusions that every $10$-principal minor of the order-$70$ matrix and every $11$-principal minor of the order-$143$ matrix is nonzero. Self-contained standard-library verifiers for the finite-field calculations accompany the paper.

math.NT↗

arXiv2026

Transferable Self-Evolving Playbooks for Agentic Security Auditing

An LLM agent for vulnerability discovery and validation is more than a model. It combines three components: an LLM for code analysis, an agent harness such as Codex or OpenCode for navigation, tool use, and execution, and an audit playbook, domain-specific procedural knowledge that guides the LLM and harness toward vulnerability discovery. Prior work relies on human-supplied playbooks, including prompt engineering, manual workflows, knowledge bases, and heuristics. This raises two research questions: Acquisition - is human curation necessary, and can playbook creation be automated? Transfer - can an evolved playbook transfer the audit procedure to weaker agents, improving their capability? We present EvoHunt, a playbook evolution environment over open-source repositories for security auditing. Three agents drive the evolution loop: an audit agent rolls out the current playbook and produces findings; an evaluator scores outcomes against ground truth; and a reviser commits updates to the playbook based on failure analysis. The playbook format is unconstrained: starting empty, EvoHunt adds or removes workflows, heuristics, vulnerability knowledge, or domain-specific content. The evolved playbook requires only minor adaptation to run under a different LLM or harness. We evaluate EvoHunt on open-source security advisories. For acquisition, playbook evolution raises end-to-end exploits for Codex/GPT5.4-xhigh 6x, from 1.1% to 6.2%, and the evolved OpenCode/GLM5.1 playbook surpasses OpenAI Codex Security on every metric, with 11.3% vs. 9.2% target-match rate, showing open-source evolution can outperform a dedicated commercial product. For transfer, the GLM-evolved playbook gives the strongest student lift: Qwen3.6-27B improves from 2.4% to 6.5%, Qwen3.6-35B-A3B from 1.1% to 4.6%, and A3B obtains 2.4x more matches than GPT transfer.

cs.CR↗

arXiv2026

When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents

Large language model agents increasingly operate through environment-facing scaffolds that expose files, web pages, APIs, and logs. These observations influence tool use, state tracking, and action sequencing, yet their reliability and authority are often uncertain. Environmental grounding is therefore a systems-level problem involving context admission, evidence provenance, freshness checking, verification policy, action gating, and model reasoning. Existing agent benchmarks mainly evaluate task capability or specific attacks such as prompt injection and memory poisoning, but they under-specify a fundamental reliability question: whether agents remain grounded in the true environment state when observations are stale, incorrect, or malicious. We introduce EnvTrustBench, an agentic framework for benchmarking this failure mode. We define an evidence-grounding defect (EGD) as a behavioral failure in which an agent treats an environment-facing claim as sufficient evidence for action without resolving it against available current evidence, leading to a task-incorrect false path under the true environment state. Given a task scenario, EnvTrustBench generates the workspace, environment, agent-facing objective, and validation oracle, executes the evaluated agent, records its action-observation trajectory and final state, and applies the oracle to produce a verdict. Using 6 LLM backbones and 5 widely used scaffolds, we evaluate 55 generated cases across 11 task scenarios, with each scenario expanded through five feedback-guided generation iterations. Results show that EGDs consistently emerge across operational workflows, highlighting environmental grounding as a core agent reliability problem with important security implications.

cs.AI↗

arXiv2026

Can Agent Benchmarks Support Their Scores? Evidence-Supported Bounds for Interactive-Agent Evaluation

Interactive agent benchmarks map an agent run to a binary outcome through outcome checks. When these checks rely on surface level signals or fail to capture the agent's actual action path, they cannot reliably determine whether the run succeeded. For example, a benchmark task may ask whether Alice's shipping address was changed, while the outcome check only verifies that the agent clicked "Save." This does not guarantee that the intended state change occurred, since the agent may have modified the wrong record. Treating such a run as successful therefore makes the reported score misleading. Benchmark quality thus depends not only on task design, but also on the reliability of outcome detection. We address this problem by introducing an outcome evidence reporting layer for existing benchmarks, without modifying their tasks, agents, or evaluators. The layer performs three functions. First, before scoring, it specifies which stored artifacts are required to verify the claimed outcome for each case. Second, it applies a locked checklist to each completed run and assigns one of three evidence labels: Evidence Pass, Evidence Fail, or Unknown. Third, it reports evidence supported score bounds that quantify uncertainty arising from Unknown cases. Rather than silently counting, discarding, or hiding uncertain cases inside a single aggregate success rate, the framework keeps them explicitly visible. We evaluate the outcome evidence layer on five public benchmarks: ANDROIDWORLD, AGENTDOJO, APPWORLD, tau3 bench retail, and MINIWOB. The resulting reports separate several empirically distinct failure modes.

cs.AI↗

arXiv2026

TxRay: Agentic Postmortem of Live Blockchain Attacks

Decentralized Finance (DeFi) has turned blockchains into financial infrastructure, allowing anyone to trade, lend, and build protocols without intermediaries, but this openness exposes pools of value controlled by code. Within five years, the DeFi ecosystem has lost over 15.75B USD to reported exploits. Many exploits arise from permissionless opportunities that any participant can trigger using only public state and standard interfaces, which we call Anyone-Can-Take (ACT) opportunities. Despite on-chain transparency, postmortem analysis remains slow and manual: investigations start from limited evidence, sometimes only a single transaction hash, and must reconstruct the exploit lifecycle by recovering related transactions, contract code, and state dependencies. We present TxRay, a Large Language Model (LLM) agentic postmortem system that uses tool calls to reconstruct live ACT attacks from limited evidence. Starting from one or more seed transactions, TxRay recovers the exploit lifecycle, derives an evidence-backed root cause, and generates a runnable, self-contained Proof of Concept (PoC) that deterministically reproduces the incident. TxRay self-checks postmortems by encoding incident-specific semantic oracles as executable assertions. To evaluate PoC correctness and quality, we develop PoCEvaluator, an independent agentic execution-and-review evaluator. On 114 incidents from DeFiHackLabs, TxRay produces an expert-aligned root cause and an executable PoC for 105 incidents, achieving 92.11% end-to-end reproduction. Under PoCEvaluator, 98.1% of TxRay PoCs avoid hard-coding attacker addresses, a +22.9pp lift over DeFiHackLabs. In a live deployment, TxRay delivers validated root causes in 40 minutes and PoCs in 59 minutes at median latency. TxRay's oracle-validated PoCs enable attack imitation, improving coverage by 15.6% and 65.5% over STING and APE.

cs.CR↗

arXiv2026

AI Agent Smart Contract Exploit Generation

Smart contract vulnerabilities have led to billions in losses, yet finding actionable exploits remains challenging. Traditional fuzzers rely on rigid heuristics and struggle with complex attacks, while human auditors are thorough but slow and don't scale. Large Language Models offer a promising middle ground, combining human-like reasoning with machine speed. Early studies show that simply prompting LLMs generates unverified vulnerability speculations with high false positive rates. To address this, we present A1, an agentic system that transforms any LLM into an end-to-end exploit generator. A1 provides agents with six domain-specific tools for autonomous vulnerability discovery, from understanding contract behavior to testing strategies on real blockchain states. All outputs are concretely validated through execution, ensuring only profitable proof-of-concept exploits are reported. We evaluate A1 across 36 real-world vulnerable contracts on Ethereum and Binance Smart Chain. A1 achieves a 63% success rate on the VERITE benchmark. Across all successful cases, A1 extracts up to \$8.59 million per exploit and \$9.33 million total. Using Monte Carlo analysis of historical attacks, we demonstrate that immediate vulnerability detection yields 86-89% success probability, dropping to 6-21% with week-long delays. Our economic analysis reveals a troubling asymmetry: attackers achieve profitability at \$6,000 exploit values while defenders require \$60,000 -- raising fundamental questions about whether AI agents inevitably favor exploitation over defense.

cs.CR↗

arXiv2025

Agentic Discovery and Validation of Android App Vulnerabilities

Existing Android vulnerability detection tools overwhelm teams with thousands of low-signal warnings yet uncover few true positives. Analysts spend days triaging these results, creating a bottleneck in the security pipeline. Meanwhile, genuinely exploitable vulnerabilities often slip through, leaving opportunities open to malicious counterparts. We introduce A2, a system that mirrors how security experts analyze and validate Android vulnerabilities through two complementary phases: (i) Agentic Vulnerability Discovery, which reasons about application security by combining semantic understanding with traditional security tools; and (ii) Agentic Vulnerability Validation, which systematically validates vulnerabilities across Android's multi-modal attack surface-UI interactions, inter-component communication, file system operations, and cryptographic computations. On the Ghera benchmark (n=60), A2 achieves 78.3% coverage, surpassing state-of-the-art analyzers (e.g., APKHunt 30.0%). Rather than overwhelming analysts with thousands of warnings, A2 distills results into 82 speculative vulnerability findings, including 47 Ghera cases and 28 additional true positives. Crucially, A2 then generates working Proof-of-Concepts (PoCs) for 51 of these speculative findings, transforming them into validated vulnerability findings that provide direct, self-confirming evidence of exploitability. In real-world evaluation on 169 production APKs, A2 uncovers 104 true-positive zero-day vulnerabilities. Among these, 57 (54.8%) are self-validated with automatically generated PoCs, including a medium-severity vulnerability in a widely used application with over 10 million installs.

cs.CR↗

arXiv2025

Evasion Under Blockchain Sanctions

Sanctioning blockchain addresses has become a common regulatory response to malicious activities. However, enforcement on permissionless blockchains remains challenging due to complex transaction flows and sophisticated fund-obfuscation techniques. Using cryptocurrency mixing tool Tornado Cash as a case study, we quantitatively assess the effectiveness of U.S. Office of Foreign Assets Control (OFAC) sanctions over a 957-day period, covering 6.79 million Ethereum blocks and 1.07 billion transactions. Our analysis reveals that while OFAC sanctions reduced overall Tornado Cash deposit volume by 71.03% to approximately 2 billion USD, attackers still relied on Tornado Cash in 78.33% of Ethereum-related security incidents, underscoring persistent evasion strategies. In this paper, we identify three significant, structural limitations in current sanction enforcement practices: (i) fragmented censorship in blockchain consensus and application layer; (ii) the complexity of obfuscation virtual asset services exploited by users; and (iii) the susceptibility of naive binary sanction classifications to dusting attacks. Our analysis and findings contribute to ongoing discussions around regulatory effectiveness in Decentralized Finance by providing empirical evidence, clarifying enforcement challenges, and informing future compliance strategies in response to sanctions and blockchain-based security risks.

cs.CR↗

arXiv2025

Decompiling Smart Contracts with a Large Language Model

The widespread lack of broad source code verification on blockchain explorers such as Etherscan, where despite 78,047,845 smart contracts deployed on Ethereum (as of May 26, 2025), a mere 767,520 (< 1%) are open source, presents a severe impediment to blockchain security. This opacity necessitates the automated semantic analysis of on-chain smart contract bytecode, a fundamental research challenge with direct implications for identifying vulnerabilities and understanding malicious behavior. Prevailing decompilers struggle to reverse bytecode in a readable manner, often yielding convoluted code that critically hampers vulnerability analysis and thwarts efforts to dissect contract functionalities for security auditing. This paper addresses this challenge by introducing a pioneering decompilation pipeline that, for the first time, successfully leverages Large Language Models (LLMs) to transform Ethereum Virtual Machine (EVM) bytecode into human-readable and semantically faithful Solidity code. Our novel methodology first employs rigorous static program analysis to convert bytecode into a structured three-address code (TAC) representation. This intermediate representation then guides a Llama-3.2-3B model, specifically fine-tuned on a comprehensive dataset of 238,446 TAC-to-Solidity function pairs, to generate high-quality Solidity. This approach uniquely recovers meaningful variable names, intricate control flow, and precise function signatures. Our extensive empirical evaluation demonstrates a significant leap beyond traditional decompilers, achieving an average semantic similarity of 0.82 with original source and markedly superior readability. The practical viability and effectiveness of our research are demonstrated through its implementation in a publicly accessible system, available at https://evmdecompiler.com.

cs.CR↗

arXiv2025

Enhancing Smart Contract Security Analysis with Execution Property Graphs

Smart contract vulnerabilities have led to significant financial losses, with their increasing complexity rendering outright prevention of hacks increasingly challenging. This trend highlights the crucial need for advanced forensic analysis and real-time intrusion detection, where dynamic analysis plays a key role in dissecting smart contract executions. Therefore, there is a pressing need for a unified and generic representation of smart contract executions, complemented by an efficient methodology that enables the modeling and identification of a broad spectrum of emerging attacks. We introduce Clue, a dynamic analysis framework specifically designed for the Ethereum virtual machine. Central to Clue is its ability to capture critical runtime information during contract executions, employing a novel graph-based representation, the Execution Property Graph. A key feature of Clue is its innovative graph traversal technique, which is adept at detecting complex attacks, including (read-only) reentrancy and price manipulation. Evaluation results reveal Clue's superior performance with high true positive rates and low false positive rates, outperforming state-of-the-art tools. Furthermore, Clue's efficiency positions it as a valuable tool for both forensic analysis and real-time intrusion detection.

cs.CR↗

arXiv2025

Blockchain Amplification Attack

Strategies related to the blockchain concept of Extractable Value (MEV/BEV), such as arbitrage, front-, or back-running create strong economic incentives for network nodes to reduce latency. Modified nodes, that minimize transaction validation time and neglect to filter invalid transactions in the Ethereum peer-to-peer (P2P) network, introduce a novel attack vector -- a Blockchain Amplification Attack. An attacker can exploit those modified nodes to amplify invalid transactions thousands of times, posing a security threat to the entire network. To illustrate attack feasibility and practicality in the current Ethereum network ("mainnet"), we 1) identify thousands of similar attacks in the wild, 2) mathematically model the propagation mechanism, 3) empirically measure model parameters from our monitoring nodes, and 4) compare the performance with other existing Denial-of-Service attacks through local simulation. We show that an attacker can amplify network traffic at modified nodes by a factor of 3,600, and cause economic damages of approximately 13,800 times the amount needed to carry out the attack. Despite these risks, aggressive latency reduction may still be profitable enough for various providers to justify the existence of modified nodes. To assess this trade-off, we 1) simulate the transaction validation process in a local network and 2) empirically measure the latency reduction by deploying our modified node in the Ethereum test network ("testnet"). We conclude with a cost-benefit analysis of skipping validation and provide mitigation strategies against the blockchain amplification attack.

cs.CR↗

arXiv2024

Smart Contract and DeFi Security Tools: Do They Meet the Needs of Practitioners?

The growth of the decentralized finance (DeFi) ecosystem built on blockchain technology and smart contracts has led to an increased demand for secure and reliable smart contract development. However, attacks targeting smart contracts are increasing, causing an estimated \$6.45 billion in financial losses. Researchers have proposed various automated security tools to detect vulnerabilities, but their real-world impact remains uncertain. In this paper, we aim to shed light on the effectiveness of automated security tools in identifying vulnerabilities that can lead to high-profile attacks, and their overall usage within the industry. Our comprehensive study encompasses an evaluation of five SoTA automated security tools, an analysis of 127 high-impact real-world attacks resulting in \$2.3 billion in losses, and a survey of 49 developers and auditors working in leading DeFi protocols. Our findings reveal a stark reality: the tools could have prevented a mere 8% of the attacks in our dataset, amounting to \$149 million out of the \$2.3 billion in losses. Notably, all preventable attacks were related to reentrancy vulnerabilities. Furthermore, practitioners distinguish logic-related bugs and protocol layer vulnerabilities as significant threats that are not adequately addressed by existing security tools. Our results emphasize the need to develop specialized tools catering to the distinct demands and expectations of developers and auditors. Further, our study highlights the necessity for continuous advancements in security tools to effectively tackle the ever-evolving challenges confronting the DeFi ecosystem.

cs.CR↗

arXiv2023

Do you still need a manual smart contract audit?

We investigate the feasibility of employing large language models (LLMs) for conducting the security audit of smart contracts, a traditionally time-consuming and costly process. Our research focuses on the optimization of prompt engineering for enhanced security analysis, and we evaluate the performance and accuracy of LLMs using a benchmark dataset comprising 52 Decentralized Finance (DeFi) smart contracts that have previously been compromised. Our findings reveal that, when applied to vulnerable contracts, both GPT-4 and Claude models correctly identify the vulnerability type in 40% of the cases. However, these models also demonstrate a high false positive rate, necessitating continued involvement from manual auditors. The LLMs tested outperform a random model by 20% in terms of F1-score. To ensure the integrity of our study, we conduct mutation testing on five newly developed and ostensibly secure smart contracts, into which we manually insert two and 15 vulnerabilities each. This testing yielded a remarkable best-case 78.7% true positive rate for the GPT-4-32k model. We tested both, asking the models to perform a binary classification on whether a contract is vulnerable, and a non-binary prompt. We also examined the influence of model temperature variations and context length on the LLM's performance. Despite the potential for many further enhancements, this work lays the groundwork for a more efficient and economical approach to smart contract security audits.

cs.CR↗

arXiv2023

Time to Bribe: Measuring Block Construction Market

With the emergence of Miner Extractable Value (MEV), block construction markets on blockchains have evolved into a competitive arena. Following Ethereum's transition from Proof of Work (PoW) to Proof of Stake (PoS), the Proposer Builder Separation (PBS) mechanism has emerged as the dominant force in the Ethereum block construction market. This paper presents an in-depth longitudinal study of the Ethereum block construction market, spanning from the introduction of PoS and PBS in September 2022 to May 2023. We analyze the market shares of builders and relays, their temporal changes, and the financial dynamics within the PBS system, including payments among builders and block proposers -- commonly referred to as bribes. We introduce an MEV-time law quantifying the expected MEV revenue wrt. the time elapsed since the last proposed block. We provide empirical evidence that moments of crisis (e.g. the FTX collapse, USDC stablecoin de-peg) coincide with significant spikes in MEV payments compared to the baseline. Despite the intention of the PBS architecture to enhance decentralization by separating actor roles, it remains unclear whether its design is optimal. Implicit trust assumptions and conflicts of interest may benefit particular parties and foster the need for vertical integration. MEV-Boost was explicitly designed to foster decentralization, causing the side effect of enabling risk-free sandwich extraction from unsuspecting users, potentially raising concerns for regulators.

cs.NI↗

arXiv2023

Blockchain Censorship

Permissionless blockchains promise to be resilient against censorship by a single entity. This suggests that deterministic rules, and not third-party actors, are responsible for deciding if a transaction is appended to the blockchain or not. In 2022, the U.S. Office of Foreign Assets Control (OFAC) sanctioned a Bitcoin mixer and an Ethereum application, putting the neutrality of permissionless blockchains to the test. In this paper, we formalize quantify and analyze the security impact of blockchain censorship. We start by defining censorship, followed by a quantitative assessment of current censorship practices. We find that 46% of Ethereum blocks were made by censoring actors that intend to comply with OFAC sanctions, indicating the significant impact of OFAC sanctions on the neutrality of public blockchains. We further uncover that censorship not only impacts neutrality, but also security. We show how after Ethereum's move to Proof-of-Stake (PoS) and adoption of Proposer-Builder Separation (PBS) the inclusion of censored transactions was delayed by an average of 85%. Inclusion delays compromise a transaction's security by, e.g., strengthening a sandwich adversary. Finally we prove a fundamental limitation of PoS and Proof-of-Work (PoW) protocols against censorship resilience.

cs.CR↗

arXiv2023

Blockchain Large Language Models

This paper presents a dynamic, real-time approach to detecting anomalous blockchain transactions. The proposed tool, BlockGPT, generates tracing representations of blockchain activity and trains from scratch a large language model to act as a real-time Intrusion Detection System. Unlike traditional methods, BlockGPT is designed to offer an unrestricted search space and does not rely on predefined rules or patterns, enabling it to detect a broader range of anomalies. We demonstrate the effectiveness of BlockGPT through its use as an anomaly detection tool for Ethereum transactions. In our experiments, it effectively identifies abnormal transactions among a dataset of 68M transactions and has a batched throughput of 2284 transactions per second on average. Our results show that, BlockGPT identifies abnormal transactions by ranking 49 out of 124 attacks among the top-3 most abnormal transactions interacting with their victim contracts. This work makes contributions to the field of blockchain transaction analysis by introducing a custom data encoding compatible with the transformer architecture, a domain-specific tokenization technique, and a tree encoding method specifically crafted for the Ethereum Virtual Machine (EVM) trace representation.

cs.CR↗

arXiv2023

SoK: Decentralized Finance (DeFi) Attacks

Within just four years, the blockchain-based Decentralized Finance (DeFi) ecosystem has accumulated a peak total value locked (TVL) of more than 253 billion USD. This surge in DeFi's popularity has, unfortunately, been accompanied by many impactful incidents. According to our data, users, liquidity providers, speculators, and protocol operators suffered a total loss of at least 3.24 billion USD from Apr 30, 2018 to Apr 30, 2022. Given the blockchain's transparency and increasing incident frequency, two questions arise: How can we systematically measure, evaluate, and compare DeFi incidents? How can we learn from past attacks to strengthen DeFi security? In this paper, we introduce a common reference frame to systematically evaluate and compare DeFi incidents, including both attacks and accidents. We investigate 77 academic papers, 30 audit reports, and 181 real-world incidents. Our data reveals several gaps between academia and the practitioners' community. For example, few academic papers address "price oracle attacks" and "permissonless interactions", while our data suggests that they are the two most frequent incident types (15% and 10.5% correspondingly). We also investigate potential defenses, and find that: (i) 103 (56%) of the attacks are not executed atomically, granting a rescue time frame for defenders; (ii) SoTA bytecode similarity analysis can at least detect 31 vulnerable/23 adversarial contracts; and (iii) 33 (15.3%) of the adversaries leak potentially identifiable information by interacting with centralized exchanges.

cs.CR↗

arXiv2023

The Blockchain Imitation Game

The use of blockchains for automated and adversarial trading has become commonplace. However, due to the transparent nature of blockchains, an adversary is able to observe any pending, not-yet-mined transactions, along with their execution logic. This transparency further enables a new type of adversary, which copies and front-runs profitable pending transactions in real-time, yielding significant financial gains. Shedding light on such "copy-paste" malpractice, this paper introduces the Blockchain Imitation Game and proposes a generalized imitation attack methodology called Ape. Leveraging dynamic program analysis techniques, Ape supports the automatic synthesis of adversarial smart contracts. Over a timeframe of one year (1st of August, 2021 to 31st of July, 2022), Ape could have yielded 148.96M USD in profit on Ethereum, and 42.70M USD on BNB Smart Chain (BSC). Not only as a malicious attack, we further show the potential of transaction and contract imitation as a defensive strategy. Within one year, we find that Ape could have successfully imitated 13 and 22 known Decentralized Finance (DeFi) attacks on Ethereum and BSC, respectively. Our findings suggest that blockchain validators can imitate attacks in real-time to prevent intrusions in DeFi.

cs.CR↗