Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Frontier AI has broken the open CTF format

kabir.au

Post reply on HN
Print view View original

31–40 of 502 posts

Re: Frontier AI has broken the open CTF format

#31

Post by koolala »

himata4113 wrote: post #21

I was writing an obfuscator recently, I just had the model deobfuscate and optimize the code back to original and I kept improving the obfuscator until it couldn't. The funny thing is that after all this I also ended up with a really strong deobfuscator and optimizer which is probably more capable than most commercial tools. The solution is just to make CTFs harder, but when do CTFs become too hard? Maybe the problem…

A portion could require astral projection and computers can't do that. Or maybe just a VR mini-game like the 90s always imagined.

Re: Frontier AI has broken the open CTF format

#32

Post by loeg »

eastbound wrote: post #29
kevinsimper wrote: post #18

You could make it offline and with provided laptops only, just like with the competitive CS2 scene.

Since real-life situations involve AI, banning AI would make CTFs just a simple game, not a demonstration of capabilities and talent.

They always were just a game?

Re: Frontier AI has broken the open CTF format

#33

Post by mort96 »

eastbound wrote: post #29
kevinsimper wrote: post #18

You could make it offline and with provided laptops only, just like with the competitive CS2 scene.

Since real-life situations involve AI, banning AI would make CTFs just a simple game, not a demonstration of capabilities and talent.

What do you mean? Solving a CTF challenge demonstrates way more capabilities and talent than just asking a chat bot to solve a CTF challenge.

Re: Frontier AI has broken the open CTF format

#34

Post by belabartok39 »

hsbauauvhabzb wrote: post #28
kevinsimper wrote: post #18

You could make it offline and with provided laptops only, just like with the competitive CS2 scene.

Ctfs need preparation and unconstrained internet, even if you block domains it’s possible to tunnel out

Use jumpbox to access CTF. Disable all wireless for the playing hall.

Re: Frontier AI has broken the open CTF format

#36

Post by sheept »

hsbauauvhabzb wrote: post #28
kevinsimper wrote: post #18

You could make it offline and with provided laptops only, just like with the competitive CS2 scene.

Ctfs need preparation and unconstrained internet, even if you block domains it’s possible to tunnel out

Presumably if you block domains, you wouldn't be able to use AI to find a way around the block. So doing so demonstrates at least some human skill

Re: Frontier AI has broken the open CTF format

#37

Post by himata4113 »

koolala wrote: post #31
himata4113 wrote: post #21

I was writing an obfuscator recently, I just had the model deobfuscate and optimize the code back to original and I kept improving the obfuscator until it couldn't. The funny thing is that after all this I also ended up with a really strong deobfuscator and optimizer which is probably more capable than most commercial tools. The solution is just to make CTFs harder, but when do CTFs become too hard? Maybe the problem…

A portion could require astral projection and computers can't do that. Or maybe just a VR mini-game like the 90s always imagined.

bringing CTF solutions into the real world is a really good idea! I didn't even think of this until you mentioned it.

we have very powerful simulation tools so something like "project a pattern at these angles" wouldn't really work as you could simulate that.

I guess something cool is that we can make simulating the solution very expensive, but in real world it would be free since it's analog... As long as simulations take longer than it takes for a human to find a solution it would be a pretty good way to deal with it. I am sure people smarter than me can come up with something.

Maybe I was too early to dismiss human creativity.

Re: Frontier AI has broken the open CTF format

#38

Post by sheept »

eecc wrote: post #17

“solve”, why not solution? Like “spend” and not expenditure, why use the verb as a noun and not care about grammar?

These examples that you're calling "verbs as a noun" are standard grammar. You can't just invent simplified rules about a language and declare it wrong when the rules fall apart.

Re: Frontier AI has broken the open CTF format

#39

Post by walletdrainer »

lukan wrote: post #5
walletdrainer wrote: post #2

>I started playing CTFs in 2021 >and the old game is not coming back For many people the CTF scene was already dead in 2021 because it had turned into something unrecognisable. In reality it’s just different.

Well, I had to google what CTF means (capture the flag, a hacking competition), so surely cannot judge here, but the text indicates that with AI some things are very different today: "That makes open CTFs pay-to-win. The more tokens you can throw at a competition, the faster you can burn down the board. Specialised cybersecurity models like alias1 by Alias Robotics are becoming less relevant compared to general front…

There are two different schools of thought:

1) It’s OK to do just about anything to win a CTF, including installing malware on the organisers computers months before the actual event so you’ll have an easy time stealing the flags.

2) It’s not ok to try and win the CTF with a solution the authors did not intend.

Recently the #2 crowd has been winning because the hacking scene has turned corporate and boring. People started to partake in CTFs in the hopes of landing a job(!)

CTFs are indeed ruined for those people, I personally don’t mind.

For the people in group #1 LLMs change little. Attacking the challenges directly was always a last resort.

Post reply on HN