Avatar

Amy Chang

Leader, Threat & Security Research

AI Software & Platform

Amy Chang is a renowned AI security and cybersecurity expert with almost two decades of practitioner, academic, and government experience. She currently leads the AI Threat Research and Security team at Cisco, developing first-in-class AI threat intelligence capabilities to monitor the threat landscape and to build defensive capabilities to secure enterprises from AI risk. Amy's work also focuses on developing scalable and sustainable frameworks for AI security. Amy is also Adjunct Faculty in Cybersecurity & Emerging Threats at Middlebury Institute of International Studies. Prior, Amy also served numerous senior roles at start-ups, corporations, government, military, and non-profits, including as an Executive Director for Global Cybersecurity Operations at JPMorgan Chase, where she led cyber threat intelligence teams and uplifted JPMorgan's intelligence-driven cybersecurity defense. She was formerly a Staff Director in the House Foreign Affairs Committee and worked on Asia policy and legislation. She also served as an officer in the U.S. Navy. Amy is a graduate of Harvard University and Brown University.

Articles

December 22, 2025

ARTIFICIAL INTELLIGENCE - AI

Cisco’s MCP Scanner Introduces Behavioral Code Threat Analysis

4 min read

A model context protocol (MCP) tool can claim to execute a benign task such as “validate email addresses,” but if the tool is compromised, it can be redirected to fulfill ulterior motives, such as exfiltrating your entire address book to an external server. Traditional security scanners could flag suspicious network calls or dangerous functions and […]

December 16, 2025

7

ARTIFICIAL INTELLIGENCE - AI

Introducing Cisco’s Integrated AI Security and Safety Framework

7 min read

The New Baseline for AI Security  AI is no longer an experimental capability or a back-office automation tool: it is becoming a core operational layer inside modern enterprises. The pace of adoption is breathtaking. Yet, according to Cisco’s 2025 AI Readiness Index, only 29 percent of companies believe they are adequately equipped to defend against […]

November 5, 2025

ARTIFICIAL INTELLIGENCE - AI
Amy Chang
Nicholas Conley

Death by a Thousand Prompts: Open Model Vulnerability Analysis

6 min read

AI models have become increasingly democratized, and the proliferation and adoption of open weight models has contributed significantly to this reality. Open-weight models provide researchers, developers, and AI enthusiasts with a solid foundation for limitless use cases and applications.  As of August 2025, leading U.S., Chinese, and European models have around 400M total downloads on […]

October 21, 2025

ARTIFICIAL INTELLIGENCE - AI

Dynamic AI Security: How Cisco AI Defense Protects Against New Threats

4 min read

Introduction The pace at which applications for artificial intelligence are evolving continues to impress. Businesses that once considered taking advantage of AI’s sophisticated predictive and natural language capabilities are now evaluating adoption of AI systems that have the ability to access internal data, make complex decisions, and have high levels of autonomy. As we continue […]

March 20, 2025

13

ARTIFICIAL INTELLIGENCE - AI
Emile Antone
Amy Chang

Cisco Introduces the State of AI Security Report for 2025: Key Developments, Trends, and Predictions in AI Security

3 min read

Cisco is proud to share the State of AI Security report covering key developments in AI security across threat intelligence, policy, and research.

September 20, 2024

ARTIFICIAL INTELLIGENCE - AI

Extracting Training Data From Chatbots

5 min read

Discover strategies for extracting training data from chatbots to enhance AI performance. Explore techniques and best practices in machine learning training.