Cybnews<p>New research out of Carnegie Mellon University is making waves! 🌊 LLMs can now autonomously plan & execute complex network attacks, even replicating the Equifax breach.</p><p>This isn't just theory – it's a critical step in understanding the evolving threat landscape and how AI could be weaponized. The flip side? Potential for autonomous security testing.</p><p>What are your thoughts on LLMs as red team agents? Dive into the details: <a href="https://engineering.cmu.edu/news-events/news/2025/07/24-when-llms-autonomously-attack.html" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">engineering.cmu.edu/news-event</span><span class="invisible">s/news/2025/07/24-when-llms-autonomously-attack.html</span></a></p><p><a href="https://defcon.social/tags/DEFCON" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DEFCON</span></a> <a href="https://defcon.social/tags/Cybersecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Cybersecurity</span></a> <a href="https://defcon.social/tags/LLM" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLM</span></a> <a href="https://defcon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://defcon.social/tags/RedTeam" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RedTeam</span></a> <a href="https://defcon.social/tags/Infosec" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Infosec</span></a> <a href="https://defcon.social/tags/CMU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>CMU</span></a> <a href="https://defcon.social/tags/NetworkSecurity" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>NetworkSecurity</span></a> <a href="https://defcon.social/tags/FutureOfHacking" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FutureOfHacking</span></a></p>