AI-driven attacks are changing the economics of cybersecurity
Stuxnet showed what a highly tailored cyberattack could achieve, but the human effort behind it made such attacks expensive and rare. AI collapses this trade-off: attacks can now combine worm-like scale with target-specific adaptation. The only thing that keeps pace with an adaptive, improving attacker is an adaptive, improving defender.
Our research
From the authors of the AI worm paper
Our founding team co-authored research demonstrating an AI-driven computer worm, malicious software that spreads between computers. The worm uses AI to tailor its attacks to each new target, rather than relying on a fixed set of preprogrammed attacks. This shows how AI could make tailored cyberattacks cheaper and easier to scale by reducing the need for human intervention.
Read the paper: AI Agents Enable Adaptive Computer Worms (arXiv)
-
“Scientists find way to supercharge dangerous computer ‘worms’ with AI”
-
“…the research is a ‘wake-up call’ to take cybersecurity risks from AI more seriously”
-
“…an AI-driven worm that can’t be stopped by patching a single flaw, because it uses reasoning to detect and exploit different vulnerabilities as it spreads”
-
“This is bigger than Mythos in my view.”
Gary McGraw, Berryville Institute of Machine Learning, in Fortune
-
“This finding catapults us into a new era of cybersecurity.”
Nicolas Papernot, co-author, in The Independent
We’re hiring members of technical staff. To apply or to get in touch, email hello [at] chrysalia.ai.