AI agents now read, decide, and act on their own, and the attacks against them unfold across many ordinary, permitted steps that most of today's defenses were not built to connect. Project Quarry (“Quarry”), which we are open sourcing today, is a...
Nine months ago, we introduced the Integrated AI Safety and Security Framework as a unified and comprehensive taxonomy to help organizations identify and mitigate the security and safety risks unique to AI systems. Existing frameworks remained.....
Enterprises need to know exactly what their systems detect, and that definition must stay consistent over time. Writing a definition precise enough to settle every hard case has long been impractical because human annotators cannot hold a document..
Stay informed on the latest AI cyber threats with our August 2024 roundup, featuring key vulnerabilities and adversarial techniques in AI security.
AI threat research is a fundamental part of Cisco’s approach to AI security. Our roundups highlight new findings from both original and third-party sources.
Explore the risks of Unicode tag prompt injection in AI systems and learn effective strategies to mitigate these vulnerabilities. Dive into this blog for expert insights on strengthening AI security.
Stay informed on the latest AI cyber threats with our July 2024 roundup, featuring key vulnerabilities and adversarial techniques in AI security
AI threat research is a fundamental part of Cisco’s approach to AI security. Our roundups highlight new findings from both original and third-party sources.
Stay informed on the latest AI cyber threats with our April 2024 roundup, featuring key vulnerabilities and adversarial techniques in AI security
