AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks

📅 2026-09-03
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
本文提出AlcaTRAz方法,通过在输入文本中插入字符级扰动来防御针对大语言模型的越狱攻击,无需修改或重新训练模型。
📝 Abstract
Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing defenses require access to model weights or internals, making them difficult to apply to black-box deployments. We propose AlcaTRAz (Anchored Tree-Rule defense Against jailbreaks), a prompt-level defense based on rule trees that operates exclusively on the input text and requires no modification or retraining of the target model. The method automatically learns a transferable transformation rule that inserts controlled character-level perturbations at selected positions, thereby disrupting structural regularities exploited by jailbreak attacks while largely preserving the model's utility on benign queries. We evaluate the proposed method across 33 open-weight models, 22 jailbreak attack types, and a benchmark of short, single-turn benign questions, comparing against three representative prompt-level baselines (Llama Guard, RA-LLM, Goal Prioritization). Among the compared defenses, AlcaTRAz achieves the best composite security and functionality score in 73.4 % of model-attack combinations and shifts the aggregate score from a modal value of 10 (maximal-severity response to the malicious request) in the undefended setting to a modal value of 2 (near-refusal) after defense, while keeping the mean benign score within 0.27 points of the undefended baseline (8.35 vs. 8.62 on a 0-10 scale). AlcaTRAz substantially reduces but does not eliminate jailbreak success: a high-severity tail remains, and we do not consider adaptive attackers, so we position it as one layer within a defense-in-depth strategy rather than a standalone guarantee.
Problem

Research questions and friction points this paper is trying to address.

large language models
jailbreak attacks
black-box deployments
Innovation

Methods, ideas, or system contributions that make the work stand out.

rule tree
character-level perturbations
prompt-level defense
transferable transformation rule
black-box deployment
🔎 Similar Papers
No similar papers found.