Prompting for Patches That Fix Vulns Without Adding New Ones - Keith Hoodlet - ASW #394
4 August - 1 hour 3 minsThere's already an increase in volume of security flaws found by LLMs. And orgs are already turning to LLMs to write code. So, what happens when orgs lean on LLMs to create patches for those security flaws? Keith Hoodlet gives an exclusive early look at his team's recent research into the success, quality, and failures of LLM-generated security patches. Notably, they saw scenarios across a spectrum from robust, effective patches to patches that changed the software's behavior to patches that introduced new vulns to patches that didn't even fix the original vuln while also introducing a new vuln.
The research considers factors like quality and correctness of prompts, complexity of the targe...
Series Episodes
Can employees safely use AI agents? AI pentesting agent liabilities, and the news - Rob Allen - ESW #473
1 hour 39 mins
24 August Finished
Surveillance, Murder Hornets, Portmantau, TrueCONF, Siemens, N-Able and More - SWN #609
41 mins
21 August Finished
Preventing a Breakout as AI Agent Threats Is One of Three Top CISO Concerns - Rob Allen - BSW #461
53 mins
19 August Finished
Secrets, Red Agent, GitHub, evoooo1bot, DecryptAds, Copilot, Aaran Leyland, and More - SWN #608
39 mins
18 August Finished
Augmenting Threat Intel Analysis with Agents - Chris Wallis, Sai Kiran Uppu, Ramin Farassat - ASW #396
1 hour 9 mins
18 August Finished
