2 papers
cs.CR2025
ModelForge: Using GenAI to Improve the Development of Security Protocols
Martin Duclos, Ivan A. Fernandez, Kaneesha Moore +2
Formal methods can be used for verifying security protocols, but their adoption can be hindered by the complexity of translating natural language protocol specifications into forma…
cs.CR2024
Poison Attacks and Adversarial Prompts Against an Informed University Virtual Assistant
Ivan A. Fernandez, Subash Neupane, Sudip Mittal +1
Recent research has shown that large language models (LLMs) are particularly vulnerable to adversarial attacks. Since the release of ChatGPT, various industries are adopting LLM-ba…