AI Agent Smart Contract Exploit Generation

• URL: http://arxiv.org/abs/2507.05558v3
• Date: Thu, 07 Aug 2025 08:29:39 GMT
• Title: AI Agent Smart Contract Exploit Generation
• Authors: Arthur Gervais, Liyi Zhou,
• Abstract summary: A1 is an agentic system that transforms any Large Language Models into an end-to-end exploit generator.<n>A1 provides agents with six domain-specific tools for autonomous vulnerability discovery.<n>We show that A1 extracts up to $8.59 million per exploit and $9.33 million total.
• Score: 8.69235891205913
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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. However, 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. Through 432 experiments across six LLMs, we show that most exploits emerge within five iterations, with costs ranging \$0.01-\$3.59 per attempt. 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.

Related papers

• Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition [101.86739402748995]
  We run the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios.<n>We build the Agent Red Teaming benchmark and evaluate it across 19 state-of-the-art models.<n>Our findings highlight critical and persistent vulnerabilities in today's AI agents.
  arXiv  Detail & Related papers  (2025-07-28T05:13:04Z)
• Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments [55.044159987218436]
  Large language models (LLMs) have demonstrated strong planning and decision-making capabilities in complex embodied environments.<n>We take a first step toward exploring the early-exit behavior for LLM-based agents.
  arXiv  Detail & Related papers  (2025-05-23T08:23:36Z)
• AegisLLM: Scaling Agentic Systems for Self-Reflective Defense in LLM Security [74.22452069013289]
  AegisLLM is a cooperative multi-agent defense against adversarial attacks and information leakage.<n>We show that scaling agentic reasoning system at test-time substantially enhances robustness without compromising model utility.<n> Comprehensive evaluations across key threat scenarios, including unlearning and jailbreaking, demonstrate the effectiveness of AegisLLM.
  arXiv  Detail & Related papers  (2025-04-29T17:36:05Z)
• Smart Contract Fuzzing Towards Profitable Vulnerabilities [10.908512696717724]
  VERITE is a profit-centric smart contract fuzzing framework.<n>It detects profitable vulnerabilities and maximizes the exploited profits.<n>It can extract more than 18 million dollars in total and is significantly better than state-of-the-art fuzzer ITYFUZZ in both detection and exploitation.
  arXiv  Detail & Related papers  (2025-01-15T14:38:18Z)
• Vulnerability anti-patterns in Solidity: Increasing smart contracts security by reducing false alarms [0.0]
  We show how integrating and extending current analyses is not only feasible, but also a next logical step in smart-contract security. We propose light-weight static checks on the morphology and dynamics of Solidity code, stemming from a developer-centric notion of vulnerability.
  arXiv  Detail & Related papers  (2024-10-22T17:21:28Z)
• All Your Tokens are Belong to Us: Demystifying Address Verification Vulnerabilities in Solidity Smart Contracts [24.881450403784786]
  Vulnerabilities in the process of address verification can lead to great security issues. We design and implement AVVERIFIER, a lightweight taint analyzer based on static EVM opcode simulation. After a large-scale evaluation of over 5 million smart contracts, we have identified 812 vulnerable smart contracts that were undisclosed by our community.
  arXiv  Detail & Related papers  (2024-05-31T01:02:07Z)
• LookAhead: Preventing DeFi Attacks via Unveiling Adversarial Contracts [15.071155232677643]
  Decentralized Finance (DeFi) has resulted in financial losses exceeding 3 billion US dollars.<n>Current detection tools face significant challenges in identifying attack activities effectively.<n>We propose LookAhead, a new framework for detecting DeFi attacks via unveiling adversarial contracts.
  arXiv  Detail & Related papers  (2024-01-14T11:39:33Z)
• How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs [66.05593434288625]
  This paper introduces a new perspective to jailbreak large language models (LLMs) as human-like communicators. We apply a persuasion taxonomy derived from decades of social science research to generate persuasive adversarial prompts (PAP) to jailbreak LLMs. PAP consistently achieves an attack success rate of over $92%$ on Llama 2-7b Chat, GPT-3.5, and GPT-4 in $10$ trials. On the defense side, we explore various mechanisms against PAP and, found a significant gap in existing defenses.
  arXiv  Detail & Related papers  (2024-01-12T16:13:24Z)
• Intention Analysis Makes LLMs A Good Jailbreak Defender [79.4014719271075]
  We present a simple yet highly effective defense strategy, i.e., Intention Analysis ($mathbbIA$)<n>$mathbbIA$ works by triggering LLMs' inherent self-correct and improve ability through a two-stage process.<n>Experiments on varying jailbreak benchmarks show that $mathbbIA$ could consistently and significantly reduce the harmfulness in responses.
  arXiv  Detail & Related papers  (2024-01-12T13:15:05Z)
• Vulnerability Scanners for Ethereum Smart Contracts: A Large-Scale Study [44.25093111430751]
  In 2023 alone, such vulnerabilities led to substantial financial losses exceeding a billion of US dollars. Various tools have been developed to detect and mitigate vulnerabilities in smart contracts. This study investigates the gap between the effectiveness of existing security scanners and the vulnerabilities that still persist in practice.
  arXiv  Detail & Related papers  (2023-12-27T11:26:26Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)
• ESCORT: Ethereum Smart COntRacTs Vulnerability Detection using Deep Neural Network and Transfer Learning [80.85273827468063]
  Existing machine learning-based vulnerability detection methods are limited and only inspect whether the smart contract is vulnerable. We propose ESCORT, the first Deep Neural Network (DNN)-based vulnerability detection framework for smart contracts. We show that ESCORT achieves an average F1-score of 95% on six vulnerability types and the detection time is 0.02 seconds per contract.
  arXiv  Detail & Related papers  (2021-03-23T15:04:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.