Microsoft publishes the 6th edition of the Cyber Signals report, which includes in particular elements (in collaboration with OpenAI) on how to protect AI platforms from emerging attacks. It notably reveals that cybercriminals are turning to AI, including LLMs, to improve their productivity and leverage platforms likely to support their objectives and attack techniques. These include reconnaissance, for example by researching the industries, locations and relationships of potential victims; code development, including improving software scripts and developing malware; and assistance with learning and using human languages and machine languages.
You can for example gain an overview of AI and LLM usage according to trending threat actors (Salmon Typhoon, Charcoal Typhoon, Crimson Sandstorm, Emerald Sleet, Forest Blizzard, etc.):
https://www.microsoft.com/en-us/security/blog/2024/02/14/staying-ahead-of-threat-actors-in-the-age-of-ai/
Microsoft works notably with the community and MITRE to integrate these tactics, techniques and procedures (TTP) related to LLM into the MITRE ATT&CK® framework or the MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems) knowledge base.
https://https://aka.ms/CyberSignalsReport-6
Jean-Francis Ahanda, Cloud and Innovation Director at ST DIGITAL
Read also :