Research
From Attack Surfaces to Actual Operations: A Survey of Modern LLM Jailbreaks
Publication date unknown · Discovered aclanthology.org
Page published
Publication date unknown · First observed: 13 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Jailbreak attacks bypass LLM safety defenses to elicit harmful outputs, and this survey's mechanism-focused taxonomy helps defenders reason systematically about attack effectiveness and mitigation strategies.
A survey paper, "From Attack Surfaces to Actual Operations: A Survey of Modern LLM Jailbreaks" by Zhou, Sun, and Meng (ACL Findings 2026), reviews existing LLM jailbreak attacks and proposes a novel two-fold taxonomy: a technical taxonomy categorizing attacks across three tiers by exploited vulnerabilities and approaches, and an operational taxonomy evaluating attacks across operational dimensions. The work argues existing taxonomies focus on manipulation methods rather than underlying mechanisms.