Beat
AI
How AI is changing attacks, defense and the security of the models themselves.
- 32
- stories
- OCT 7
- latest
All AI · page 2
Myths and Mythos: An AI Vulnerability Research FAQ
It’s still very early days for all of this, and relatively little is known about Claude Mythos’s real capabilities, so we wanted to dig into what actually is known and what it all means.
Dennis Fisher · 6 min
Anthropic’s Claude Mythos is Just the Beginning
Anthropic’s Project Glasswing initiative, announced this week, sent shockwaves across the cybersecurity world.
Lindsey O'Donnell-Welch · 3 min
Command Injection Bug in OpenAI Codex Exposed GitHub OAuth Tokens
The bug is a command injection issue and lies in the way that Codex processed GitHub branch names during the execution of tasks.
Dennis Fisher · 3 min
For AI and Security, ‘The Storm is Coming’
Technology moves quickly, and as we’re discovering yet again, threat actors move just as quickly, and are adopting AI tools and platforms at an astonishing rate.
Dennis Fisher · 3 min
Mister Decipher’s Neighborhood
It’s a beautiful day in the neighborhood for hacking! Come along on a magical adventure as Mr. Decipher teaches you about the dangers of brute-force attacks!
Dennis Fisher · 1 min
Microsoft Disrupts RedVDS Cybercrime Platform
The takedown marks a significant blow to the cybercrime-as-a-service ecosystem, which fuels large-scale, automated fraud.
Dennis Fisher · 3 min
Q&A: Sean Zadig of Yahoo on Employing AI in Security
There are plenty of challenges and pitfalls for security teams looking to deploy AI tools and Zadig said Yahoo is taking a measured, careful approach. This is a condensed and edited portion of our discussion.
Dennis Fisher · 4 min
Google: Threat Actors Testing AI During Malware Execution
Threat actors are now using LLMs in malware during execution, as a way to alter the malware’s behavior to enable detection evasion and more.
Lindsey O'Donnell-Welch · 3 min
With AI and Security, ‘Everyone is Still Learning’
For many organizations, the biggest potential risk that arises from the use of AI tools is the leakage or mishandling of sensitive data.
Dennis Fisher · 3 min
Why WarGames is Still Predicting the Future 40 Years Later
WarGames may be 42 years old but its prescience about our current technocracy and race to take humans out of the loop is as clear as ever
Dennis Fisher · 1 min
New Automated npm Attack Campaign Targets Dozens of Packages
The campaign does not appear to be connected to the previous npm phishing attacks, but it does seem to be related to a rash of GitHub and npm token and secret thefts from the end of August.
Dennis Fisher · 3 min
The Emerging Ecosystem Dedicated to AI Accountability
A new ecosystem of security researchers is emerging, looking to sniff out data security and privacy issues in AI systems and grappling with issues like a lack of transparency into and understanding of LLMs.
Lindsey O'Donnell-Welch · 7 min
