面向推理的编程:通过链式语义工具来突破大型视觉语言模型
Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
AI总结:
本文提出面向推理的编程方法,通过链式语义工具突破大型视觉语言模型的安全对齐。
摘要:
大型视觉语言模型(LVLMs)经过安全对齐以抑制有害内容。然而,当前的防御措施主要针对输入表示中的显式恶意模式,往往忽略了组合推理中的固有漏洞。在本文中,我们发现了一个系统性缺陷,即LVLMs可以被诱导从良性前提中合成有害逻辑。我们正式将这种攻击范式定义为"面向推理的编程",并借鉴系统安全中的Return-Oriented Programming进行结构类比。正如ROP通过链式良性指令序列绕过内存保护,我们的方法利用模型的指令遵循能力,通过语义碰撞来协调正交的良性输入。我们通过\tool{}自动化框架实例化这种范式,该框架优化了"语义正交性"和"空间隔离"。通过生成与有害意图语义解耦的视觉工具,并安排它们以防止早期特征融合,\tool{}迫使恶意逻辑只在后期推理过程中出现。这有效地绕过了感知层面的对齐。我们评估\tool{}在SafeBench和MM-SafetyBench上,针对7种最先进的0.LVLMs,包括GPT-4o和Claude 3.7 Sonnet。我们的结果表明,\tool{}能够持续绕过安全对齐,其在开源模型上平均比现有最强基线高出4.67%,在商业模型上高出9.50%。
英文摘要:
Large Vision-Language Models (LVLMs) undergo safety alignment to suppress harmful content. However, current defenses predominantly target explicit malicious patterns in the input representation, often overlooking the vulnerabilities inherent in compositional reasoning. In this paper, we identify a systemic flaw where LVLMs can be induced to synthesize harmful logic from benign premises. We formalize this attack paradigm as \textit{Reasoning-Oriented Programming}, drawing a structural analogy to Return-Oriented Programming in systems security. Just as ROP circumvents memory protections by chaining benign instruction sequences, our approach exploits the model's instruction-following capability to orchestrate a semantic collision of orthogonal benign inputs. We instantiate this paradigm via \tool{}, an automated framework that optimizes for \textit{semantic orthogonality} and \textit{spatial isolation}. By generating visual gadgets that are semantically decoupled from the harmful intent and arranging them to prevent premature feature fusion, \tool{} forces the malicious logic to emerge only during the late-stage reasoning process. This effectively bypasses perception-level alignment. We evaluate \tool{} on SafeBench and MM-SafetyBench across 7 state-of-the-art 0.LVLMs, including GPT-4o and Claude 3.7 Sonnet. Our results demonstrate that \tool{} consistently circumvents safety alignment, outperforming the strongest existing baseline by an average of 4.67\% on open-source models and 9.50\% on commercial models.
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。