Adversarial Intelligence: Red Teaming Malicious Use Cases for AI

New research from Recorded Futures Insikt Group outlines a collaborative investigation by threat intelligence analysts and R&D engineers into the potential malicious uses of artificial intelligence (AI) by threat actors. They experimented with a variety of AI models, including large language models, multimodal image models, and text-to-speech models, without any fine-tuning or additional training, to mimic the resources threat actors might realistically have.

Their findings suggest that in 2024, the most probable malicious applications of AI will be through targeted …

adversarial ai models amp analysts artificial artificial intelligence cases engineers fine-tuning futures image insikt group intelligence investigation language language models large malicious malware analysis red teaming research speech text threat threat actors threat intelligence use cases