Ethereum Foundation says AI agents find real bugs, but most are false positives
The Ethereum Foundation said AI agents are good at finding vulnerabilities in the network infrastructure, but most are false positives, according to a blog posted Thursday.
"Agents finding bugs wasn't the surprise. The surprise was how little of the work went into finding them, and how much went into telling the real bugs from the ones that just looked real," the EF said.
The EF's Protocol Security team has been using coordinated AI agents to test critical network infrastructure, including systems software, cryptographic code and smart contracts. The agents have found real bugs, including "a remotely-triggerable panic in libp2p's gossipsub, a core part of the peer-to-peer layer Ethereum consensus clients run on," which has been fixed and publicly disclosed.
While the foundation said AI agents can quickly pinpoint potential vulnerabilities, the technology has simultaneously created a larger workload for human researchers, who must evaluate a growing number of potential bugs, or "candidates."
"Most candidates are wrong, duplicate, or out of scope. That's not a problem with the method; that's how it works," the EF wrote. "The goal is to reject the wrong ones fast and back the real ones with proof that's hard to argue with."
A potential vulnerability isn't considered a real finding until researchers can independently reproduce the failure against the actual code. The foundation also noted that AI agents can struggle to identify bugs that emerge across a sequence.
In other words, some of Ethereum's top security researchers consider AI to be a strong search tool, but not an oracle, so to speak.
"The time that used to go into coming up with and chasing down hypotheses now goes into judging them at scale, including building the oracle, running the triage, keeping the list of known issues, and handling disclosure," they said. "The bottleneck didn't go away. It moved from finding bugs to trusting the results, which is a better place for it, because that's where human judgment actually matters."
Thursday's blog comes on the heels of the EF's recent reorganization, which resulted in a new operational structure and the foundation shedding 20% of its total workforce.
Disclaimer: The content of this article solely reflects the author's opinion and does not represent the platform in any capacity. This article is not intended to serve as a reference for making investment decisions.
You may also like
Wall Street giants collectively raise rate hike forecasts, US Treasury futures continue to fall, gold drops over 1% to break 4000
After the US October CPI exceeded expectations, Goldman Sachs and Nomura added a forecast for an interest rate hike in March next year, while Deutsche Bank included a forecast for a rate hike in January next year. Currently, the market has fully priced in a 25 basis point rate hike in December, with a 13% probability for a 50 basis point hike. On Wednesday, the US Treasury spot market was closed, but Treasury futures continued to fall, with corresponding yields rising by about 2 to 4 basis points, and spot gold came under pressure, dropping by 1.1%.
No Need to Worry About the Cooling Down of AI Data Center Construction? The US Import Boom Is Unlikely to Subside in the Short Term, Real Impact May Come in 2029
It takes an average of 4.8 years from finalizing investment to starting construction of a data center project, and an additional 2.6 years from construction start to becoming operational. Servers usually cannot be installed until after the building structure and racks are completed. For trade partners such as Taiwan (China), South Korea, and Mexico who rely on US data center supply chain demand, the inertia in construction timelines provides at least a one- to two-year buffer for future exports.
Federal Reserve Major Debate: When Should the Tenure of “Number Three” Williams End?
The main point of contention is whether Williams should step down in June 2028, upon completing a full 10-year term, or in June 2027, when he reaches the mandatory retirement age of 65. Analysts point out that the Federal Reserve Board holds ultimate discretion; if he leaves early, Fed Chair Waller would be able to assert greater control over the appointment to this critical position. However, forcing Williams to shorten his term could easily be interpreted as political manipulation. Williams himself is expected to serve until June 2028.
Crypto prices
More
