Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2402.16192/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTDefending Large Language Models against Jailbreak Attacks via Semantic Smoothing — mentioned by mapmeldhttps://news.ycombinator.com/item?id=42161547urn:hackerpapers:mention:2402.16192:42161547Sun, 17 Nov 2024 02:39:09 GMT<p>There are some authors in common with a more recent paper &quot;Defending Large Language Models against Jailbreak Attacks via Semantic Smoothing&quot; https://arxiv.org/abs/2402.16192</p><p><a href="https://hackerpaper.kaipfister.de/p/2402.16192/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL