This paper reveals that while inference-time scaling can enhance robustness in open-source models, it also introduces security risks when intermediate reasoning steps are accessible to adversaries.

https://arxiv.org/abs//2507.15974

YouTube: https://www.youtube.com/@ArxivPapers

TikTok: https://www.tiktok.com/@arxiv_papers

Apple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016

Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers