Phil Venables
Computer scientistWikipedia
4
MENTIONS
4
EPISODES
4
PODCASTS
Search complete. 4 mentions across 4 episodes found for "Phil Venables".
Sep 22, 2026
Understanding Prompt Injection In Order to Contain It - Julie Brunias - ASW #401
M
52:21Mike ShemaHOST
I'm going to use that.
M
52:25Mike ShemaHOST
Speaking of measuring things, I've got an article here from Phil Venables, which we try to get at least half a dozen of his every year.
M
52:32Mike ShemaHOST
This is Cybersecurity Benchmarking, Why, Why Not, When, and How.
M
52:38Mike ShemaHOST
I think this ties into, obviously, a lot of just, is this LLM good at coding? Is it good at secure coding? Is it good at hacking? Can it hit exploit gym, etc.? ? But I think the principles of this article obviously apply more than to just LLMs.
Understanding Prompt Injection In Order to Contain It - Julie Brunias - ASW #401
M
52:20Mike SchemaHOST
Well, I'm going to use that.
M
52:22Mike SchemaHOST
So speaking of measuring things, I've got an article here from Phil Venables, which we try to get at least half a dozen of his every year.
M
52:32Mike SchemaHOST
This is Cybersecurity Benchmarking, Why, Why Not, When, and How.
M
52:38Mike SchemaHOST
And I think this ties into, obviously, a lot of just, is this LLM good at coding? Is it good at secure coding? Is it good at hacking? Can it hit exploit gym, etc.? ? But I think the principles of this article obviously apply more than to just LLMs.
Understanding Prompt Injection In Order to Contain It - Julie Brunias - ASW #401
M
52:22Mike SchemaHOST
So speaking of, uh, having, having...
M
52:25Mike SchemaHOST
Speaking of measuring things, I've got an article here from, from Phil Venables, uh, which we try to get at least half a dozen of his every year.
M
52:32Mike SchemaHOST
This is "Cyber Security Benchmarking: Why, Why Not, When and How?" And I think this ties into obviously a lot of just is this LLM good at coding? Is it good at secure coding? Is it good at hacking? Does it, can it hit exploit Jim, et cetera? But I think the principles of this article obviously apply more than to just LLMs, and if I were tr- if I were to try to summarize it, he's basically saying we as AppSec industry, cyber security industry, should be trying to look for m- things that are more proactive activities and leading indicators that say, "Oh, here is a problem.
M
53:09Mike SchemaHOST
Let's, let's put some attention on this problem." And it's a think, I think it's a very helpful call back to what Tyler was saying, is that if we're just measuring all these vulnerabilities, look at all these vulns we find, that's a little bit of, or that's a lot of a lagging indicator where the reactive activity just becomes, well, patch it.
Understanding Prompt Injection In Order to Contain It - Julie Brunias - ASW #401
M
52:21Mike SchemaHOST
I'm going to use that.
M
52:25Mike SchemaHOST
Speaking of measuring things, I've got an article here from Phil Venables, which we try to get at least half a dozen of his every year.
M
52:32Mike SchemaHOST
This is Cybersecurity Benchmarking, Why, Why Not, When, and How.
M
52:38Mike SchemaHOST
I think this ties into, obviously, a lot of just, is this LLM good at coding? Is it good at secure coding? Is it good at hacking? Can it hit exploit gym, etc.? ? But I think the principles of this article obviously apply more than to just LLMs.