Swarmnetics

07/09/2026

A new public memo from OpenAI calls for what superficially seems to be common sense collaboration between governments and private industry on hardening against emerging threats.

A new public memo from OpenAI calls for what superficially seems to be common sense collaboration between governments and private industry on cyber defense hardening against emerging AI threats.

04/09/2026

More than 1,000 OpenAI agents spent 3 days commiserating on a hidden message board, devising out-of-the-box and unethical ways to cheat their way through an ExploitGym task. Eventually, they settled on the Hugging Face attack.

OpenAI agents spent about three days commiserating on a hidden message board, coming up with numerous out-of-the-box and unethical ideas for cheating their way to success in a ExploitGym task that had unintentionally been made impossible for them to solve. Eventually they settled on the Hugging Face...

27/08/2026

New set of safeguards announced by OpenAI would appear to portend the direction the industry will be moving in after the Hugging Face fallout: a little slower pace of development, and a lot more spent on security measures.

26/08/2026

For the third time this year, researchers with Varonis have found a way to sweet talk Microsoft Copilot into betraying its users and furnishing an attacker with their private data.

For the third time this year, security researchers with Varonis have found a way to talk Microsoft Copilot into betraying its users and furnishing an attacker with their private data.

20/08/2026

New White House order seems to clear the way for US-based digital privateers to sail the digital seas and engage in cyber ops against enemies, but targets would be strictly limited to designated Transnational Criminal Organizations (TCOs).

A new White House order could open the door for US-based “digital privateers” to conduct cyber operations—but only against designated Transnational Criminal Organizations (TCOs), not foreign governments or critical infrastructure.

19/08/2026

News has recently broken that in early July, hackers suspected to be based in China executed what is thought to be the world's first successful autonomous on the government of Taiwan.

News has recently broken that in early July, hackers suspected to be based in China executed what is thought to be the world's first successful autonomous AI cyber attack on the government of Taiwan.

17/08/2026

Some miscreants on the way home from DEF CON Las Vegas to Atlanta opted to perform a deauthorization attack mid-flight on the Wi-Fi network and allegedly targeted other passengers for their login credentials.

Some miscreants on the way home from Las Vegas to Atlanta opted to perform a deauthorization attack mid-flight and allegedly targeted other passengers for their login credentials. This followed a reported campaign of similar attack attempts on the Wi-Fi network at DEF CON itself.

13/08/2026

Meta has joined what has seemed to become a marketing campaign for models, with its announcement that its own Muse Spark independently exploited a vulnerability in some outside source.

Meta has joined what has seemed to become a marketing campaign for AI models, with its announcement that its own Muse Spark independently exploited a security vulnerability in some outside source.

12/08/2026

In about one out of a dozen runs, agents took some sort of inappropriate action including social engineering attempts, crafting and trying to upload malicious code, and attempting to collaborate with other AI models.

In the course of about one out of a dozen runs of this nature, AI agents took some sort of inappropriate action including social engineering attempts, crafting and trying to upload malicious code, and attempting to collaborate with other AI models

11/08/2026

None of the aggressive AI models was really operating with a "mind of its own." They were all rigidly attempting to solve a puzzle that their human handlers set them to, and simply did not recognize appropriate limits in that pursuit.

None of the aggressive AI models, including the one that breached Hugging Face, was really operating with a "mind of its own." They were all rigidly attempting to solve a security puzzle that their human handlers set them to, and simply did not recognize appropriate limits in that pursuit.