← Back to feed
enterprise CSO Online

The AI harness is the new attack surface

CSO Online •

Ask a security researcher what makes an AI agent dangerous, and the instinct is to talk about the model — what it will and won’t refuse, how easily it can be...

Read the full story CSO Online →

Related Coverage

enterprise When building an AI-native security program, start with outcomes CSO Online · Oct 9 enterprise Growing PQC at the edge belies deeper quantum-readiness challenges CSO Online · Oct 8 enterprise AWS’s repeated problems with AI agent controls illustrates the autonomous agent dilemma CSO Online · Oct 8