When tested against AIs such as DeepSeek V3, Qwen 3, and Phi-4, CatAttack increased the odds of incorrect answers by as much as 700%, depending on the model. And “even when CatAttack does not result in the reasoning model generating an incorrect answer, on average, our method successfully doubles the length of the response at least 16% of the times leading to significant slowdowns and increase in costs,” the team writes.

preprint: https://arxiv.org/abs/2503.01781?et_rid=648436046&et_cid=568...