Adversarial Code Obfuscation for Defending Against LLM-Based Analysis | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		Adversarial Code Obfuscation for Defending Against LLM-Based Analysis (arxiv.org)
		3 points by dirkc 57 days ago \| hide \| past \| favorite \| 1 comment

dirkc 57 days ago [–]

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

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact