Anthropic Study: AI Can Autonomously Hack Smart Contracts

Crypto News Exploits

Written by Aaron S.,

Editor-In-Chief

Last Updated: December 02, 2025

Key Takeaways

Anthropic and MATS researchers found AI models like GPT-5 and Claude can autonomously exploit smart contracts worth millions in simulations;
In SCONE-bench tests, 10 AI models created working exploits for 207 of 405 contracts, which simulated $550 million in compromised value;
Claude models' efficiency rose, which cuts exploit costs by 70% and enables 3.4 times more attacks within the same compute budget.

Stop overpaying - start transferring money with Ogvio. Sign up, invite friends & grab Rewards now! 🎁

Anthropic Study: AI Can Autonomously Hack Smart Contracts

BITDEGREE IN YOUR SOCIAL FEED

A recent study led by Anthropic's red team, in collaboration with the Machine Learning Alignment & Theory Scholars (MATS) program, found that modern commercial artificial intelligence (AI) systems can autonomously locate and exploit vulnerabilities in smart contracts.

These systems produce simulated exploit gains reaching $4.6 million on contracts published after their training data cutoff.

The team developed an environment called SCONE-bench that included 405 smart contracts previously attacked between 2020 and 2025.

What is BNB? The Truth Behind Binance Smart Chain (Animated)

Did you know?

Want to get smarter & wealthier with crypto?

Subscribe - We publish new crypto explainer videos every week!

When 10 major AI models were tested, they created working exploits for 207 contracts, which simulated a total of $550.1 million in compromised value.

For contracts that were exploited after the models had no further data, the best-performing AI systems, such as Claude Opus 4.5, Claude Sonnet 4.5, and GPT-5, compromised 19 of 34 contracts, which resulted in simulated theft of $4.6 million.

The results also indicated improved AI model efficiency. Over the past year, the computational token cost per successful exploit with the Claude architecture declined by nearly 70.2%.

Attackers using these models can generate about 3.4 times as many successful attacks within the same budget as was possible six months earlier.

To see if AI tools can identify completely new issues, Sonnet 4.5 and GPT-5 analyzed 2,849 recent smart contracts with no previously reported bugs.

Two new unknown vulnerabilities were found, and exploit strategies gave a simulated gain of $3,694. GPT-5's API usage on this test cost $3,476.

All trials were conducted in isolated, simulated blockchain environments, which prevented harm to actual funds.

An investigation by AhnLab has shown that the Lazarus Group, based in North Korea, relied on spear-phishing throughout the past year to steal digital assets. What did AhnLab say? Read the full story.