Improving Decompiled Code Readability with LLM Agents - SecTalks SYD0x68 (104th)

Improving Decompiled Code Readability with LLM Agents

Presents our research on our paper releases earlier this year where we identified a practical approach to improving decompiler output using large language models guided by quantitative readability metrics. The research shows that LLMs can make decompiled code significantly easier to understand, but success depends on providing a clear, measurable definition of readability. Without that guidance, models often struggle to maintain direction over complex tasks, fail to complete them consistently, or optimise for the wrong objective.

Link to paper: https://arxiv.org/abs/2606.06838

Speakers: Niel Archibald, Ruben Thijssen

How to find us on the day?

An organiser will be on the ground floor until 6:15 to assist attendees with accessing the lifts.

Speed hiring

There is an opportunity for potential employers to do an impromptu 30-second description of their open role. If you are interested, speak with one of the organisers before the start of the session.

Please note the best way to support SecTalks and tell others about your open roles is through sponsorship. We encourage companies, small or large, to come forward and support their local community.

Sponsors

• SecDim (Connect)

• Google (LinkedIn)

• Atlassian (LinkedIn)

Notes

• For sponsoring SecTalks Sydney and supporting the non-profit community, contact sydney@sectalks.org

• To speak or submit CTF challenges at SecTalks, fill up https://sessionize.com/sectalks

Thanks to you for

1. Keeping your RSVP up-to-date. We are usually overbooked and have a long waitlist. We will sign you in and keep track of RSVPs and attendance.

2. Aligning with SecTalks no-bullshit code of conduct

3. Keeping the venue nice and tidy during and after the session