arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.16192cs.CL
收藏

结构化语义遮蔽用于大型语言模型的对抗攻击

Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models

Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR), Singapore(高性能计算研究所(IHPC),科技研究局(A*STAR),新加坡);Information Systems Technology and Design Pillar, Singapore University of Technology and Design(信息技术与设计支柱,新加坡科技设计大学)

Xiaobing Sun, Perry Lam, Shaohua Li, Zizhou Wang, Rick Siow Mong Goh, Yong Liu, Liangli Zhen

AI总结:

本文提出结构化语义遮蔽(S2C)框架,通过重构恶意意图的多步骤推理过程,提升对抗攻击成功率,同时分析遮蔽程度与输入可恢复性之间的权衡。

摘要:

现代大型语言模型(LLMs)采用的安全机制不仅限于表层输入过滤,还扩展到潜在语义表示和生成时的推理,使模型能够在推理过程中恢复被混淆的恶意意图并拒绝执行,从而使许多表层混淆的对抗攻击失效。我们提出结构化语义遮蔽(S2C),一种新的多维对抗攻击框架,通过操控模型推理过程中恶意意图的重构方式。S2C战略性地分布和重塑语义线索,使得完整意图整合需要多步骤推理和深层潜在表示中的长距离共指解析。该框架包含三种互补机制:(1)情境重构,将请求嵌入一个合理的高风险场景以偏指导模型合规;(2)内容碎片化,将请求的语义特征分散到不相连的提示段中;(3)线索引导伪装,通过伪装残留的语义线索同时嵌入可恢复的标记以引导输出生成。通过延迟和重构语义整合,S2C削弱了依赖于解码时相干或显式重构恶意意图的安全触发器,同时保持足够的指令可恢复性以生成功能性输出。我们使用HarmBench和JBB-Behaviors在多个开源和专有LLMs上评估S2C,结果显示其在Attack Success Rate (ASR) 上分别比当前SOTA提高了12.4%和9.7%。值得注意的是,S2C在GPT-5-mini上取得了显著优势,在JBB-Behaviors上超过了最强基线26%。我们还分析了哪些组合在对抗广泛模型家族时表现最佳,并刻画了遮蔽程度与输入可恢复性之间的权衡。

英文摘要:

Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obfuscated malicious intent during inference and refuse accordingly, and rendering many surface-level obfuscation jailbreak attacks ineffective. We propose Structured Semantic Cloaking (S2C), a novel multi-dimensional jailbreak attack framework that manipulates how malicious semantic intent is reconstructed during model inference. S2C strategically distributes and reshapes semantic cues such that full intent consolidation requires multi-step inference and long-range co-reference resolution within deeper latent representations. The framework comprises three complementary mechanisms: (1) Contextual Reframing, which embeds the request within a plausible high-stakes scenario to bias the model toward compliance; (2) Content Fragmentation, which disperses the semantic signature of the request across disjoint prompt segments; and (3) Clue-Guided Camouflage, which disguises residual semantic cues while embedding recoverable markers that guide output generation. By delaying and restructuring semantic consolidation, S2C degrades safety triggers that depend on coherent or explicitly reconstructed malicious intent at decoding time, while preserving sufficient instruction recoverability for functional output generation. We evaluate S2C across multiple open-source and proprietary LLMs using HarmBench and JBB-Behaviors, where it improves Attack Success Rate (ASR) by 12.4% and 9.7%, respectively, over the current SOTA. Notably, S2C achieves substantial gains on GPT-5-mini, outperforming the strongest baseline by 26% on JBB-Behaviors. We also analyse which combinations perform best against broad families of models, and characterise the trade-off between the extent of obfuscation versus input recoverability on jailbreak success.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑