D-INFK news channel
All stories by Leonid Leiva Ariosa
SPY Lab researchers first to ever peek into ChatGPT’s black box
- Spotlight
- Computer Security and Privacy Group
- Artificial intelligence
- Institute of Information Security
- Security
- Machine learning
- Front – Spotlight
In a world-first, researchers from the SPY Lab led by Professor Florian Tramèr along with collaborators have succeeded in extracting secret information on the large language model behind ChatGPT. The team responsibly disclosed the results of their “model stealing attack” to OpenAI. Following the disclosure, the company immediately implemented countermeasures to protect the model.
by Leonid Leiva Ariosa