<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Jailbreak on The Engine Room</title><link>/en/tags/jailbreak/</link><description>Recent content in Jailbreak on The Engine Room</description><generator>Hugo -- 0.155.3</generator><language>en-us</language><lastBuildDate>Sat, 22 Nov 2025 15:00:00 +0300</lastBuildDate><atom:link href="/en/tags/jailbreak/index.xml" rel="self" type="application/rss+xml"/><item><title>Defending MLLMs from Implicit Jailbreak Attacks</title><link>/en/notes/defence_mllm_from_jailbreak/</link><pubDate>Sat, 22 Nov 2025 15:00:00 +0300</pubDate><guid>/en/notes/defence_mllm_from_jailbreak/</guid><description>A new class of attacks where text and image look safe separately, but their combination carries malicious meaning</description></item><item><title>External Data Extraction Attacks against RAG</title><link>/en/notes/data_extraction_attacks_against_rag/</link><pubDate>Fri, 14 Nov 2025 15:00:00 +0300</pubDate><guid>/en/notes/data_extraction_attacks_against_rag/</guid><description>The paper studies a new class of attacks against RAG-type systems</description></item><item><title>Fine-Tuning Jailbreaks</title><link>/en/notes/fine_tuning_jailbreaks/</link><pubDate>Mon, 10 Nov 2025 15:00:00 +0300</pubDate><guid>/en/notes/fine_tuning_jailbreaks/</guid><description>The paper discusses vulnerabilities in fine-tuning systems for large language models under conditions close to real-world operation</description></item></channel></rss>