{"id":59139,"date":"2025-08-06T21:00:15","date_gmt":"2025-08-06T21:00:15","guid":{"rendered":"https:\/\/www.threatshub.org\/blog\/microsoft-researchers-bullish-on-ai-security-agent-even-though-it-let-74-of-malware-slip-through\/"},"modified":"2025-08-06T21:00:15","modified_gmt":"2025-08-06T21:00:15","slug":"microsoft-researchers-bullish-on-ai-security-agent-even-though-it-let-74-of-malware-slip-through","status":"publish","type":"post","link":"https:\/\/www.threatshub.org\/blog\/microsoft-researchers-bullish-on-ai-security-agent-even-though-it-let-74-of-malware-slip-through\/","title":{"rendered":"Microsoft researchers bullish on AI security agent even though it let 74% of malware slip through"},"content":{"rendered":"

Microsoft has rolled out an autonomous AI agent that it claims can detect malware without human assistance.<\/p>\n

The prototype, called Project Ire<\/a>, reverse engineers software “without any clues about its origin or purpose,” and then determines if the code is malicious or benign, using large language models (LLM) and a bunch of callable reverse engineering and binary analysis tools.<\/p>\n

“It was the first reverse engineer at Microsoft, human or machine, to author a conviction case \u2014 a detection strong enough to justify automatic blocking \u2014 for a specific advanced persistent threat (APT) malware sample, which has since been identified and blocked by Microsoft Defender,” Redmond claimed in a Tuesday blog post.<\/p>\n