IIIT Hyderabad developing tool to detect bugs in AI-generated software code

IIIT-Hyderabad researchers are developing an automated system to detect bugs in AI-generated and concurrent software code. The project focuses on ensuring “correctness by construction” and aims to identify errors early using advanced testing techniques

Hyderabad: As AI is being increasingly used for writing software programs, a new challenge has emerged over whether such automatically generated code is safe, reliable and correct besides being free of bugs.

To tackle this challenge, researchers at the International Institute of Information Technology (IIIT) Hyderabad are developing an automated system that can detect bugs in software development, particularly in modern software that run many tasks simultaneously.

---

According to Prof Abhishek Singh of Software Engineering Research Centre at IIIT – Hyderabad, many software bugs originate long before code is written. “Many software bugs find their roots in the transition from informal intent to formal implementation. They begin with how humans describe what they want the software to do. The problem arises because you never describe your intent clearly,” he said.

Rather than fixing bugs after software is written, Prof Singh advocates for an approach known as “correctness by construction”. This involves expressing a programmer’s intent in a formal, precise way, often directly within the code itself, using specifications and assertions that computers can check automatically.

The challenge becomes far more complex when software runs tasks simultaneously, as most modern systems do. “If automated bug detection is hard in sequential programs, it becomes even harder and non-intuitive in parallel programs,” said Prof Singh. To address this, his team uses fuzzing, a technique which automatically generates a large number of inputs to test how a software behaves.

The automated bug detection project, according to IIIT-Hyderabad, is being carried out in collaboration with Prof Ashish Mishra of IIT Hyderabad, along with students from both IIT and IIIT-H working on it full-time.

While still in its early stages, the team is building a practical tool that works on real software. Rather than generating random inputs blindly, the tool uses formal knowledge of how concurrent programs behave on real hardware to explore the most error-prone scenarios.

“We are targeting commonly used programming languages like C and modern architectures like x86 and ARM,” Prof Singh said.