Papers by Harshith Vaddiparthy
Research Square, 2025
This paper presents a proof-of-concept study evaluating Claude Opus 4.1's capabilities in securit... more This paper presents a proof-of-concept study evaluating Claude Opus 4.1's capabilities in security vulnerability generation and detection through a meta-experimental approach. We systematically generated 75 security vulnerabilities across five Python web applications (2,146 lines of code) spanning SQL injection, XSS, authentication bypass, path traversal, and command injection categories. We then evaluated the AI's ability to conduct security audits of its own generated code, producing 1,892 lines of detailed analysis. Although this circular validation approach has inherent limitations, it reveals the AI's pattern recognition capabilities and security principle understanding. The system successfully identified all intentionally created vulnerabilities and provided structured remediation guidance. This work provides initial evidence of AI potential for security code analysis and establishes a methodology for evaluating AI security comprehension, though real-world validation with independent code remains essential.
This paper presents a novel meta-experimental approach to analyzing the debugging capabilities of... more This paper presents a novel meta-experimental approach to analyzing the debugging capabilities of large language models (LLMs), specifically Claude 3 Opus. Through a carefully designed experiment where the AI system first generates intentionally buggy code and subsequently debugs it without prior knowledge, we document and analyze the systematic debugging methodology employed by modern AI systems. Our experiment involved a Python-based Task Management System containing 12 distinct bug categories, ranging from syntax errors to complex runtime issues. The AI successfully identified and resolved all bugs using a methodical, error-driven approach that mirrors human debugging strategies. Key findings include the AI's ability to: (1) prioritize syntax errors before runtime issues, (2) leverage Python's error messages effectively, (3) implement comprehensive fixes with proper error handling, and (4) validate solutions through automated testing. This research contributes to understanding AI's role in automated software debugging and has implications for the future of AI-assisted software development, code review processes, and programming education.
Uploads
Papers by Harshith Vaddiparthy