למה פריצות צלחו בדגמי שפה דיפוזיים: ניתוח נוף אנרגטי

תקציר מקורי באנגליתarXiv:2609.30841v1 Announce Type: new Abstract: Existing attacks and defenses for diffusion-based large language models (dLLMs) target specific vulnerabilities but lack a shared framework explaining why attacks succeed. We propose one by interpreting safety alignment as shaping the denoising energy landscape: a well-aligned model routes harmful queries toward safe outputs through an energy barrier that separates the two regions. Current jailbreak attacks reduce to two strategies for circumventing this barrier: obscuring the query's safety disposition at initialisation, or intervening mid-trajectory to force the denoising path across the energy barrier. From this perspective and the result that masked diffusion models minimise kinetic energy during denoising, we derive three complementary,