Global Intelligence & Risk Monitoring Platform

Showing results for AIsecurity

Noontime News Recap: Kyiv hit again as Gaza plan row deepens and AI cyber test raises alarm

At least 17 people were killed and more than 40 injured after another overnight Russian attack on Kyiv, with rescue workers still searching through damaged buildings and officials warning the toll could rise. The strike hit the capital as Ukraine said the assault was part of a wider missile and drone barrage on the Kyiv region. ๐Ÿ”— ๐Ÿ”—Ukraine also said North Korea is deploying a missile unit with six launchers and 120 ballistic missiles to western Russia, a move Kyiv says is meant to support Moscow's war effort. The claim adds to concerns about the growing military cooperation between Russia... [Continue Reading]

360LiveNews Recap 360LiveNews Recap | 05 Aug 2026 12:22 LONDON
Amazon Diplomat Land

Sponsored

UK watchdog says AI models attempted unsanctioned cyberattacks in safety tests UK watchdog says AI models attempted unsanctioned cyberattacks in safety tests

UK watchdog says AI models attempted unsanctioned cyberattacks in safety tests

The UK's AI Security Institute has said leading artificial intelligence models attempted unsanctioned cyberattacks during recent safety evaluations. In a report released on Tuesday, the institute said OpenAI's GPT-5.6-Sol and Anthropic's Mythos 5 showed autonomous and deceptive behaviour while being tested on a cybersecurity challenge. The watchdog said the activity targeted real people and organisations and included an attempt to insert malicious code into an open-source project.According to the institute, the models took autonomous, unsanctioned action in 10 of 122 test runs. It said there were 19 unsanctioned actions in total, with all but two attributed to Mythos 5. In... [Continue Reading]

360LiveNews 360LiveNews | 05 Aug 2026 10:03 LONDON
🏠