Avatar

Ehsan Aghaei

AI Researcher

AI Software and Platform

Ehsan Aghaei is a Senior LLM Research Scientist at Cisco, where he drives innovation in applied artificial intelligence for cybersecurity within Cisco AI Defense. He specializes in the design and advancement of large language models and intelligent systems for AI validation, domain-specific language modeling, advanced model tuning, and agentic AI—enhancing Cisco’s capabilities in robust, explainable, and resilient AI-driven cybersecurity automation. Ehsan’s work bridges foundational research and applied engineering, enabling next-generation AI systems that advance threat reasoning, vulnerability assessment, and autonomous cyber defense at scale. Prior to joining Cisco, Ehsan was a Postdoctoral Fellow at Carnegie Mellon University’s School of Computer Science, where he contributed to several prestigious and high-impact national research programs in collaboration with DARPA, NASA JPL, NSF, ONR, ARO, and PNNL. His efforts focused on AI-driven vulnerability analysis, semantic modeling for cyber threat intelligence, attack-path analysis, and the development of intelligent deception and adaptive defense systems leveraging natural language understanding. Ehsan has authored numerous peer-reviewed publications, holds multiple patents, and has open-sourced several AI models advancing the intersection of large language models and cybersecurity innovation.

Articles

Defining Model Provenance: A Constitution for AI Supply Chain Safety and Security

5 min read

When it comes to AI models, one of the hardest questions to answer is deceptively simple: where did this model actually come from? We addressed part of this problem with Model Provenance Kit, an open-source tool that fingerprints models at the.....

Introducing Model Provenance Kit: Know Where Your AI Models Come From

7 min read

The importance of understanding a model’s origins has been a frequent topic of discussion among researchers and industry experts, and our own AI research confirms that AI supply chain security remains a weak link. Tracking where models come from....

SecureBERT 2.0: Cisco’s next-gen AI model powering cybersecurity applications

4 min read

Today, we are excited to share that the SecureBERT 2.0 model is available on HuggingFace and GitHub with an accompanying research paper. This release marks a significant milestone, building on the already widely adopted SecureBERT model to unlock even more advanced cybersecurity applications. Just see this unparalleled performance across real-world tasks: In 2022, the first […]