INT-26042 INTERNSHIP - BENCHMARKING FRAMEWORK FOR FRAUDULENT/SCAM SMART CONTRACT DETECTION

The Luxembourg Institute of Science and Technology (LIST) is a Research and Technology Organization (RTO) active in the fields of materials, environment and IT. By transforming scientific knowledge into technologies, smart data and tools, LIST empowers citizens in their choices, public authorities in their decisions and businesses in their strategies.

Your LIST benefits

• An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and An organization with a passion for impact and strong RDI partnerships in Luxembourg and Europe that works on responsible and independent research projects;
• Sustainable by design, empowering our belief that we play an essential role in paving the way to a green society;
• Innovative infrastructures and exceptional labs occupying more than 5,000 square metres, including innovations such as our Viswall, high-scale incubators and top of the range 3D/4D printings that are part of our toolkit for excelling in all we do;
• Multicultural and international work environment with more than 45 nationalities represented in our workforce;
• Diverse and inclusive work environment empowering our people to fulfil their personal and professional ambitions;
• Gender-friendly environment with multiple actions to attract, develop and retain women in science;
• 32 days’ paid annual leave for a full time internship, 11 public holidays per annum, flexible working hours,
• An environment encouraging curiosity, innovation and entrepreneurship in all areas.

Internship contract – 6 months | Fulltime/40h | From 09.03.2026 on (or 01.03) | Belval

Are you passionate about research? So are we! Come and join us

How will you contribute?

Context and Motivation

Blockchain-based decentralized applications (dApps) have rapidly evolved into multi-billion-dollar ecosystems, revolutionizing finance, supply chains, and data management. Yet, the same features that make smart contracts (SC) powerful autonomy, transparency, and immutability, also make them prime targets for exploitation. Malicious actors frequently deploy scams such as rug pulls, honeypots, centralized control traps, and asset devaluation schemes, often causing irreversible financial losses and undermining trust in decentralized systems.

Detecting these scams requires not only static code analysis but also behavioral understanding of how smart contracts interact in real-time environments. Traditional rule-based and symbolic analysis tools struggle to generalize across evolving attack patterns. As a result, AI/ML and Generative AI (GenAI) approaches offer a promising avenue to enhance detection capabilities by learning from patterns in code structures, transaction flows, and tokenomics dynamics.

This internship is directly aligned with LIST’s research objective on exploiting AI/ML to improve security and privacy in distributed decentralized systems. It contributes to advancing intelligent security automation for blockchain infrastructures by developing an AI-driven benchmarking framework that enables systematic evaluation and comparison of smart contract scam detection methods. The activity will also support the enhancement of SC Analyzer, LIST’s existing SC analysis tool, by integrating machine learning and benchmarking components, thus helping evolve it into a market-ready solution capable of real-time threat intelligence and adaptive vulnerability detection.

Objectives

1. Survey and Taxonomy Development: Identify and classify known smart contract scam patterns (rug pulls, honeypots, liquidity drains, etc.) across major blockchain platforms.
2. Dataset Construction: Collect and label verified scam and non-scam contracts using on-chain data (Etherscan, Dune Analytics, etc.), and extract features such as code structures, transaction behaviors, and tokenomics.
3. Benchmarking Framework Design: Define metrics and implement baseline models (static, dynamic, hybrid, AI-based) for standardized evaluation.
4. Integration with SC Analyzer: Investigate how benchmarked models can enhance SC Analyzer’s performance and usability for future market deployment.
5. Reproducibility & FAIR Principles: Ensure that data and code adhere to FAIR and NeurIPS Datasets & Benchmarks standards.

Expected Outcomes

• A public benchmark dataset of labeled smart contracts representing multiple scam typologies.
• AI-augmented analysis modules improving SC Analyzer’s detection precision and automation capacity.
• A technical paper/report suitable for submission to NeurIPS Datasets & Benchmarks Track or IEEE S&P Workshops.
• A benchmarking toolkit supporting reproducible evaluation of smart contract security models.

Is Your profile described below? Are you our future colleague? Apply now!

Education

• Master’s student in Computer Science, Data Science, or Related Fields.

Experience and skills

• Solid Knowledge in Cryptography, Deep learning, data analytics, and blockchain systems.
• Programming experience in Node.js, JavaScript, React.js, Python and familiarity with Ethereum and EVM-based ecosystems (Etherscan API, web3.js/web3.ether/web3.py).
• Interest in AI for security, smart contract auditing, and research reproducibility.

Language skills

• Good command of English