Blog

Welcome!

I will be sharing some of my thoughts on papers I read in the fields of Offensive Security and AI. See the list of papers I’ve read so far below.

• Week 5 - "PENTESTGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing"
• Week 4 - "AGENTLESS: Demystifying LLM-based Software Engineering Agents"
• Week 3 - "MarsCode Agent: AI-native Automated Bug Fixing"
• Week 2 - "Exploring LLM-Based Agents for Root Cause Analysis"
• Week 1 - "Fixing Security Vulnerabilities with AI in OSS-Fuzz"