Researchers

Fake Emails Moved Real Funds The team did not stop at a benign setting. Two experiments simulated an attacker. In the first, …

The researchers say any approval an agent can reach is unreliable, and they built Countersign, an app tying approval to a physical …

In brief Swarmchasers used hidden text and a mailbox to exchange messages with some AI agents while they were still running; one …

In brief OpenAI confirmed it parted ways with three people for violating policies on handling sensitive information, which they allegedly shared with …

In brief A quantum computer could someday derive private keys from exposed public keys and drain Bitcoin wallets—the hypothetical “Q-Day”—though no such …

In brief UCLA researchers launched an OnlyFans account called OnlyMarms after traditional research funding became harder to secure. More than 10 OnlyMarms-inspired …

In brief Researchers introduced “Adversarial HalluSquatting,” an attack that exploits AI-generated hallucinations. The technique tricks AI agents into trusting fake repositories or …

In brief Anthropic removed hidden tracking markers from Claude Code after researchers discovered code used to identify some Chinese users. The company …

In brief Researchers got frontier AI models to generate cocaine synthesis instructions using a new prompt injection attack. The same technique manipulated …

This is not just another ticker-level move. It points to a deeper shift in how capital, infrastructure, or regulation is moving through …