Live data from Hacker News

Adversarial Code Obfuscation for Defending Against LLM-Based Analysis

Post reply on HN

Print view View original

1–2 of 2 posts

Adversarial Code Obfuscation for Defending Against LLM-Based Analysis

#1

Post by dirkc » Thu, Jul 30, 2026, 1:40 PM UTC

Adversarial Code Obfuscation for Defending Against LLM-Based Analysis
arxiv.org

Re: Adversarial Code Obfuscation for Defending Against LLM-Based Analysis

#2

Post by dirkc » Thu, Jul 30, 2026, 2:02 PM UTC

I'm curious about ways to entice agents to perform weird and wacky things when working on a codebase.

Post reply on HN