2025 Annual Report

The State of AI Security

Artificial intelligence has emerged as one of the defining technologies of the 21st century, yet the AI threat landscape is novel, complex, and not effectively addressed by traditional cybersecurity solutions.

Cisco's inaugural State of AI Security report aims to provide a comprehensive overview of important developments in AI security across several key areas: threat intelligence, policy, and research. The goal is to empower the community to better understand the AI security landscape so that companies are better equipped to manage the risks and reap the benefits that AI brings.

The State of AI Security report will cover:

  • Important developments in U.S. and international AI policy, highlighting common themes and macro trends from hundreds of AI-related legislation, executive orders, partnership agreements, and security frameworks.
  • In-depth analysis of threats to AI infrastructure, AI supply chains, and AI applications and the evaluation of the implications AI threat vectors such as model backdoors, prompt injections, and data extraction.
  • Original research into algorithmic jailbreaking, data set poisoning, data extraction, and several other cutting-edge AI security topics led by Cisco's AI research team.
Show more
Cisco would like to use your information above to provide you with the latest offers, promotions, and news regarding Cisco products and services. You can unsubscribe at any time. See Cisco's Online Privacy Statement for more information.