Studying Underground Market for LLMs, Researchers Find OpenAI Models Power Malicious Services

Caute_cautim — Sun, 21 Jan 2024 23:31:18 GMT

Hi All

Well we all knew the underground would grasp the mettle and adapt OpenAI models for malicious usage.

Great insights.

In what the researchers call a first-of-a-kind study, Zilong Lin, Jian Cui, Xiaojing Liao, and XiaoFeng Wang from Indiana University Bloomington examined 212 real-world “Mallas”– their term for LLMs used for malicious services – “uncovering their proliferation and exposing their operational modalities.” The study, titled “Malla: Demystifying Real-world Large Language Model Integrated Malicious Services,” provides a glimpse into the challenges of AI safety while pointing to practical solutions to make LLMs safer for public use. And, it notes the important role that general purpose models– particularly ones developed by OpenAI– play in serving as the back-end for tools and services with names like BadGPT, XXXGPT, and Evil-GPT.

https://www.techpolicy.press/studying-black-market-for-large-language-models-researchers-find-openai-models-power-malicious-services/

Regards

Caute_Cautim

topic Studying Underground Market for LLMs, Researchers Find OpenAI Models Power Malicious Services in Threats

Studying Underground Market for LLMs, Researchers Find OpenAI Models Power Malicious Services