Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

Understand

Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks.

• Unfortunately, we find that the same improved capabilities amplify the dual-use risks for malicious purposes of these models.
• Dual-use is difficult to prevent as instruction-following capabilities now enable standard attacks from computer security.
• The capabilities of these instruction-following LLMs provide strong economic incentives for dual-use by malicious actors.