Microsoft says poisoned AI acts normal until a trigger word makes it 'blow up'
… During the RSAC 2026 cybersecurity conference, Microsoft told me it believes it’s found an indicator that ordinary folks can spot in the wild. …
Search
Anthropic's new AI found thousands of zero-day flaws on its own
… To do so, we need to make progress in developing cybersecurity and other safeguards that detect and block the model's most dangerous outputs. …
A Microsoft expert casually dropped this big tip for safe AI use
… While at this year’s RSAC cybersecurity conference, I chatted with Ram Shankar Siva Kumar, Microsoft's Data Cowboy and AI Red Team Lead, who dropped a ton of facts about the behind-the-scenes work of securing AI—and a big tip on staying safe while exploring this rapidly growing area of technology. …
Microsoft says you're asking the wrong question about AI
… But after talking with Microsoft at RSAC’s 2026 cybersecurity conference, I realized I’ve been approaching that question all wrong. You probably have, too. Ram Shankar Siva Kumar, Data Cowboy and AI Red Team Lead at Microsoft, says most people ask the question of how to trust an AI. …
Trusting AI is dangerous. It's time for an open-source revival
… My time covering cybersecurity keeps driving home this point. …
Even trusted apps can spread PC malware now
… You only install apps from known storefronts—Microsoft, Steam, etc. …
I trust these 7 antivirus software suites to keep my Windows PC safe
… Is Windows 10/11's built-in Microsoft Defender antivirus enough, or should you pay for more? While Windows Security which includes Microsoft Defender performs well, the best third-party antivirus software have even higher rates of detecting threats. …