Cisco Blogs
Ben Risher
Ben Risher
AI Researcher, AI Threat Research and Security
AI Software and Platform
Ben Risher is an AI researcher specializing in adversarial machine learning and AI red teaming at Cisco, where he serves on the AI Threat Research and Security team. With over a decade of offensive security experience spanning zero-day research, reverse engineering, traditional red teaming, and tool development, Ben applies his offensive expertise to emerging AI/ML security challenges. His research focuses on AI security threats through development of scalable red teaming tools and discovery of novel exploitation techniques against language models and AI agents.
Ben is the creator of feroxbuster, a high-performance offensive security tool trusted by security professionals worldwide. He also maintains several open-source security projects and has contributed to frameworks like Metasploit, ExploitDB, and LibAFL. Previously, Ben founded and led Salesforce's AI Red Team, architected the fuzzai security suite for automated AI/ML testing, and conducted vulnerability research for government and private sector clients. An active contributor to both academic and industry security communities, Ben bridges the gap between cutting-edge AI research and real-world offensive security operations.
Articles
Artificial intelligence and machine learning (AI/ML) models are increasingly shared across organizations, fine-tuned, and deployed in production systems. Cisco’s AI Defense offering includes a model file scanning tool designed to help organizations detect and mitigate risks in AI supply chains by verifying their integrity, scanning for malicious payloads, and ensuring compliance before deployment. Strengthening our […]
