This paper explores filtering dual-use topics from training data to enhance the tamper-resistance of open-weight AI systems, demonstrating significant improvements in adversarial fine-tuning resistance without degrading unrelated capabilities.

https://arxiv.org/abs//2508.06601

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