Want to create an interactive transcript for this episode?
Podcast: Arxiv Papers
Episode: Does More Inference-Time Compute Really Help Robustness?
Description: 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//2507.15974YouTube: https://www.youtube.com/@ArxivPapersTikTok: https://www.tiktok.com/@arxiv_papersApple Podcasts: https://podcasts.apple.com/us/podcast/arxiv-papers/id1692476016Spotify: https://podcasters.spotify.com/pod/show/arxiv-papers