Vol. II · No. 156
Established 2025

smallweb

Friday, June 5, 2026
160 writers in the library
Tech · 1 shelves
Tech

Sean Heelan.

Security research, vulnerability analysis, and AI in security.

Recent essays

10 of 10

On the Coming Industrialisation of Exploit Generation with LLMs

Recently I ran an experiment where I built agents on top of Opus 4.5 and GPT-5.2 and then challenged them to write exploits for a zeroday vulnerability in the QuickJS Javascript interpreter. I added a variety of modern exploit mitigations, various constraints…

How I used o3 to find CVE-2025-37899, a remote zeroday vulnerability in the Linux kernel’s SMB implementation

In this post I’ll show you how I found a zeroday vulnerability in the Linux kernel using OpenAI’s o3 model. I found the vulnerability with nothing more complicated than the o3 API – no scaffolding, no agentic frameworks, no tool use. Recently I’ve been auditin…

Application optimisation with LLMs: Finding faster, equivalent, software libraries.

A few months back I wrote a blog post where I mentioned that the least-effort/highest reward approach to application optimisation is to deploy a whole-system profiler across your clusters, look at the most expensive libraries & processes, and then search Googl…

Finding 10x+ Performance Improvements in C++ with CodeQL – Part 2/2 on Combining Dynamic and Static Analysis for Performance Optimisation

In the previous post I advocated for building systems that combine static and dynamic analysis for performance optimisation. By doing so, we can build tools that are much more useful than those focused on either analysis approach alone. In fact, for many stati…

60%+ Performance Improvements with Continuous Profiling and Library Matching – Part 1/2 on Combining Dynamic and Static Analysis for Performance Optimisation

This is the first post in a two part series on combining static and dynamic analyses for performance optimisation. I’ve split them up as otherwise it’ll be horrifically long, and the second post will be online later this week. This post lays out some high leve…

Optimising an eBPF Optimiser with Prodfiler (Repost)

How do you almost 2x your application’s performance with zero code changes? Read on to find out! This is a repost of a blog I originally wrote on prodfiler.com on October 4th 2021. Prodfiler was acquired by Elastic is is now the Elastic Universal Profiler. In…

PhD Thesis: Greybox Automatic Exploit Generation for Heap Overflows in Language Interpreters

Over the summer I defended my PhD thesis. You can find it here. To give a super quick summary (prior to a rather verbose one ;)): Pre-2016 exploit generation was primarily focused on single-shot, completely automated exploits for stack-based buffer overflows i…

Gollum: Modular and Greybox Exploit Generation for Heap Overflows in Interpreters

At the upcoming ACM Conference on Computer and Communications Security (CCS) I’ll be presenting a paper on Automatic Exploit Generation (AEG), with the same title as this blog post. You can find the paper here. In the paper I discuss a system for automatically…

Automation in Exploit Generation with Exploit Templates

At last year’s USENIX Security conference I presented a paper titled “Automatic Heap Layout Manipulation for Exploitation” [paper][talk][code]. The main idea of the paper is that we can isolate heap layout manipulation from much of the rest of the work involve…

Some Cool Projects from a Dagstuhl Seminar on SAT, SMT and CP

I was lucky enough to attend a Dagstuhl seminar titled “Bringing CP, SAT & SMT Together” earlier this week, and learned about some really cool work I hadn’t previously heard of, especially in the realm of constraint satisfaction and optimization. There were pl…