Math Jailbreaking Prompts
Free while signed in. Answers cite the passages they came from.
First page
The curator’s take
uses GPT-4o to generate mathematically encoded prompts that serve as an effective jailbreaking technique; shows an average attack success rate of 73.6% across 13 state-of-the-art; this highlights the inability of existing safety training mechanisms to generalize to mathematically encoded inputs.
Every Monday
Get next week’s papers.
The same picks and the same summaries, in your inbox. Free, and 176 issues deep.
Subscribe on Substack