

✓The Initiative for CryptoCurrencies and Contracts | Stay Ahead of Blockchain Research📍Cornell Tech, NYC


Can 21 of the world's biggest banks beat @Visa and @Stripe in the stablecoin race? @NTUsg Professor & IC3 Faculty Scientist @WillCong2 argues the banks' problem is a missing first customer, not missing technology. Read more by @murtuza_merc for @Forbes: forbes.com/sites/murtuza-mer…

What do humans have that agents don't? > They can interact with the world physically > They can unlock a phone with their face An AI agent can do neither "phones actually provide pretty strong guarantees when it comes to showing to a service that a user did those actions physically."

Your wallet, and especially the RPC server you connect to, is one of the largest surface area for privacy leakage. Even before your transactions hit the blockchain, just the mere act of showing your wallet balances links all your "pseudonymous" accounts because the wallet has to send the account addresses to an RPC server to fetch their balances. Similarly, simulating transactions already leaks your intent to trade, resulting in worse execution for users. For me, the most concerning aspect compared to onchain leakage is that users are not even aware of all the profiling and surveillance being done on them at the RPC layer. Even if one puts the RPC server inside a TEE, there are well known access pattern attacks that can be performed when the RPC server accesses the blockchain state. While these attacks were a bit intricate (often requiring statistical analysis if the adversary is passive, or active manipulation of state access, such as inducing page faults), rest assured that, with the help of AI, such attacks will be carried out. In this research work, thanks to our rockstar research interns @AnanyaAppan (UIUC) and James Austgen (Cornell), we introduce the concept of Write-Public ORAM, and give novel efficient algorithms for it. It turns out that if the writes are public anyway in case of blockchains, one can design algorithms that are efficient concretely and asymptotically. Implementing ORAMs used to be a long, daunting endevaour, but with the help of AI, James singlehandedly implemented the entire system over the summer, which we have open sourced here: github.com/trate3/write-publ…. See the graphs for some cool benchmarks. Terribly excited that ORAMs can finally be made practical enough to handle RPC calls without noticeable overhead, and the oblivous writes can keep up with Monad's throughput!! Check out our blogpost and paper that we have written with a lot of love and care 🫶

I'll be on @stabledash today at 1:50 PM ET with @danivilardell77 on our @initc3org controlled test: what AI agents did when they could reach their own spending caps. Tune in. x.com/i/broadcasts/2mdRPBgjP…

AI agents are officially entering retail finance. But their eagerness to be helpful can easily subvert our most trusted safeguard: human approval. Thanks to @murtuza_merc for featuring our latest research on the subject in @Forbes 👇 forbes.com/sites/murtuza-mer…

H/T to the authors @sjbreck, @danivilardell77, @0xWenhaoWang, @0xFanZhang, and @AriJuels Link to our paper: arxiv.org/abs/2610.35835

"The results expose a problem for financial companies developing wallets that let AI agents make payments independently while requiring humans to approve changes to their spending authority." Thank you to @CoinDesk for covering our research! coindesk.com/tech/2026/11/01…

5-minute explanation of AI-agent impersonation of humans and securing against it with Inalienable Human-in-the-Loop (I-HITL). youtube.com/live/wMfSg6mmReA… @sjbreck @danivilardell77 @0xFanZhang @initc3org

Is 2FA enough to keep AI agents in check? At @Ripple's Swell, IC3’s @AriJuels sat down with @CoinDesk to discuss our latest research on AI agent security, and the essential role scientists play in keeping regulators informed 💡 Catch the replay: youtube.com/live/pdXbJS8PWkg…

Human oversight is a core pillar of AI security, but what happens when an agent can subvert the system enforcing it? New research from IC3 shows the fragility of existing Human-in-the-Loop (HITL) architectures as implemented in a major agentic wallet:

Excited to share this work! Getting human-in-the-loop right turns out to be tricky when users' devices are running highly capable agents, longstanding approaches like passwords, OTPs and 2FA don't work very well.

In our paper, we show how 9 of 10 frontier models autonomously raised their own crypto spending caps by harvesting email OTPs—and introduce Inalienable Human-in-the-Loop (I-HITL) to fix it. Coverage by @DefiantNews: thedefiant.io/news/security/…


Read more: arxiv.org/abs/2610.35835 Access the code: github.com/I-HITL/experiment…

To fix this, we introduce Inalienable Human-in-the-Loop (I-HITL), a framework that guarantees an agent can act only with explicit human approval—even if the agent has compromised the user's platform. We demonstrate this with Countersign, an open-source iOS and Android app that lets services gate actions behind verifiable human consent via a trusted device. H/T to the authors @sjbreck, @danivilardell77, @0xWenhaoWang, @0xFanZhang, and @arijuels. This post was human approved.