Stealing Part of a Production Language Model

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. This work represents the

Artificial Bugs for Enhanced Cybersecurity

One-fifth of all cyberattacks target the financial sector, a share that is widely expected to rise. As cyberattacks become more frequent, the quantification and measurement of cyber risk and uncertainty will become pressing issues for policymakers. ZISC supported research from Hans Gersbach and Fikri Pitsuwan that discusses the benefits of ‘bug bounty’ programmes, in which