Adversarial Attacks
WHY THIS MATTERS IN BRIEF Like software AI can have bugs in it toO, and while these are generally exploited in a different way by…
WHY THIS MATTERS IN BRIEF AI can do a lot of weird things, like make its own languages, evolve, replicate, and encrypt comms, now there’s…
WHY THIS MATTERS IN BRIEF AI’s are powerful and capable, and that extends to helping terrorists plan their next ATTACKS … Love the Exponential…
WHY THIS MATTERS IN BRIEF AI guardrails don’t just have to apply to one language – they have to apply to all languages, all dialects,…
WHY THIS MATTERS IN BRIEF If you change one pixel in an image neural networks misclassify it, and hackers are taking advantage. Now there might…
WHY THIS MATTERS IN BRIEF Is human psychology the next great weapon in trying to get AI’s to do things their guardrails are supposed to…
WHY THIS MATTERS IN BRIEF AI can be hacked, fooled, broken, and scammed into behaving badly and that’s a big problem that companies are trying…
WHY THIS MATTERS IN BRIEF AI is easily tricked so Anthropic have given their AI a “Constitution” to follow meaning it has the capacity to…
WHY THIS MATTERS IN BRIEF Guardrails on AI work, kind of, but the SANS Institute were still able to get ChatGPT to create Ransomware for…
WHY THIS MATTERS IN BRIEF As the radio spectrums get more crowded we need a new way to keep our communications systems working, and AI…
WHY THIS MATTERS IN BRIEF DeepFakes will be with us for the rest of eternity, and they’ll get easier to create, so in the future…
WHY THIS MATTERS IN BRIEF As more of the world comes to rely on AI adversarial attacks pose a particular challenge to companies and people…
