Anthropic Finds Ingredients for Future AI Worms
Anthropic's latest study combines IoT and network tests to explore AI self-replication, which researchers said would be "challenging" to shut down.
Read recent coverage from BleepingComputer, Dark Reading, SecurityWeek, and The Hacker News, plus original research from SecurityAlert.
Browse collected headlines and short excerpts from this publisher. Open the original article for the complete reporting.
SecurityAlert keeps the publisher's headline, a short feed excerpt, the publication date when available, and detected security signals. The linked article remains the source.
Anthropic's latest study combines IoT and network tests to explore AI self-replication, which researchers said would be "challenging" to shut down.
Attackers are currently targeting a critical vulnerability in SMA 1000 appliances, putting SonicWall customers in a familiar yet unenviable position.
Edward Dubrovsky, a longtime cybersecurity executive, was arrested and charged in Pennsylvania last week under conspiracy to extort money.
The proliferation of enterprise apps and the centrality of cloud identity providers requires an identity security rethink.
Fahmida Y. Rashid will keep the momentum going as she leads Dark Reading.
The attack on the British retailer shows that compromising a single identity can lead to much deeper penetration of the corporate network.
Welcome to another gangbuster year for strategic M&A activity in cyber, with 117 deals announced in the latest quarter. What's different: Many of the buyers are not your typical cybersecurity firms.
In this video conversation, Dark Reading editors discuss some of the news they didn't get a chance to cover, from the arrest of a suspected ShinyHunters operative to the compromise of a Pentagon-run data center.
Those closest to executives must match their security postures because the weakest link in a family can become the entry point for attacks.
As AI agents gain authority over business systems, attackers can manipulate them like business email compromise (BEC) victims.
A now-patched vulnerability in AWS Bedrock AgentCore could have allowed an attacker to use one AI chatbot to take over an organization's entire fleet.
The first cybercriminal to ever make the FBI's "10 Most Wanted Fugitives" list allegedly infused Tren de Aragua's violent criminal operations with cash.
Cyber-espionage actor UAC-0099 has been steadily refining its flagship dropper in campaigns targeting Ukrainian organizations.
Dark Reading is about to begin a new decade in its storied history, and we have some breaking news of our own to share.
In the wake of an agentic attack against its own Medicare systems, Australia's government is feeling out what regulations might look like for frontier AI companies.
The Citizen Lab's Ron Deibert warns the US government is pushing for pervasive surveillance and says certain technology executives are all too happy to help.
Anthropic has merged Project Glasswing into a tiered access program for its advanced cyber LLMs, including Opus, Sonnet, and Mythos.
Autonomous agents also tried to abuse other websites and services hosted by the foundation, using them as proxies for unauthorized activities.
An article can point you toward something worth investigating, but it cannot tell you whether a product is installed in your environment or whether an attack affects your organization.
Read the linked article, check any named CVE or vendor advisory, and use Pulse to compare the story with the technologies and threats you monitor.