Anthropic is finding bugs faster than Microsoft can fix them
On an afternoon in mid-May, dozens of Microsoft engineers and their managers gathered online and in a conference room at the company’s Redmond, Washington, headquarters…
On an afternoon in mid-May, dozens of Microsoft engineers and their managers gathered online and in a conference room at the company’s Redmond, Washington, headquarters…
Last week’s unprecedented security event in which two OpenAI security hacking models trespassed into the network of fellow AI company Hugging Face was enabled by…
Microsoft said MDASH with MAI-Cyber-1-Flash received a 96 percent score on CyberGYM, a standard benchmark test. The rating is 12 points higher than Anthropic’s Mythos…
In early 2025, Atlanta resident Samuel Tunick was on his way home following a trip abroad. After landing in the US, customs agents demanded access…
New safeguards focused on “active monitoring” and “improved alignment” helped drastically reduce unintended actions by its models, OpenAI said. New safeguards focused on “active monitoring”…
The new study takes a first look at one piece of that exposure: what actually sits inside the apps built and marketed specifically for the…
Nearly half of companies that are targets of a ransomware cyber attack end up paying a ransom to release their data or systems, according to…
One of the Russian government’s most elite hacking groups has adopted an attack, known as Clickfix, to compromise devices belonging to sensitive organizations in Ukraine,…
“If I can set up the system so that it runs my code when the admin user logs in,” the attacker has de facto administrator…
Further complicating the process, even the expiration of the Microsoft certificate that signed the shims, which took place late last month, isn’t enough to revoke…
The federal government is warning users of home and small office routers to secure their devices as Russia state hackers continue to mass-compromise them for…
Prompt injections, the malicious commands attackers embed into content to entice LLMs to follow them, have been attackers’ go-to tool for turning AI platforms against…