基准测试针对多模态大语言模型的煤气灯否定攻击
Benchmarking Gaslighting Negation Attacks Against Multimodal Large Language Models
AI总结:
本研究系统研究多模态大模型在对话中因用户否定而反转正确输出的煤气灯否定攻击,提出首个基准GaslightingBench,发现专有模型韧性优于开源模型,且主观领域更脆弱,凸显鲁棒性差距。
摘要:
多模态大语言模型(MLLMs)在整合不同模态方面展现出显著的进步,在复杂理解与生成任务中表现出色。尽管取得了成功,MLLMs仍然容易受到对话式对抗性输入的影响。在本文中,我们系统地研究了煤气灯否定攻击:这是一种现象,即模型尽管最初提供了正确答案,却被用户提供的否定说法说服而反转其输出,常常编造理由。我们对多种基准上的最先进MLLMs进行了广泛评估,并观察到当引入否定时性能显著下降。值得注意的是,我们引入了首个基准GaslightingBench,专门设计用于评估MLLMs对否定论点的脆弱性。GaslightingBench包含从现有数据集中精选的多项选择题,以及跨20个不同类别生成的否定提示。在广泛的评估中,我们发现专有模型如Gemini-1.5-flash和GPT-4o相比开源对应模型如Qwen2-VL和LLaVA表现出更好的韧性,尽管即使是像Gemini-2.5-Pro这样的高级推理导向模型仍然容易受到影响。我们的类别级分析进一步表明,主观或社会细微领域(例如,社会关系、图像情感)尤其脆弱,而更客观的领域(例如,地理)表现出相对较小但仍然显著的下降。总体而言,所有评估的MLLMs在煤气灯否定攻击下都难以维持逻辑一致性。这些发现突显了一个基本的鲁棒性差距,并为开发更可靠和值得信赖的多模态AI系统提供了见解。项目网站:https://yxg1005.github.io/GaslightingNegationAttacks/。
英文摘要:
Multimodal Large Language Models (MLLMs) have exhibited remarkable advancements in integrating different modalities, excelling in complex understanding and generation tasks. Despite their success, MLLMs remain vulnerable to conversational adversarial inputs. In this paper, we systematically study gaslighting negation attacks: a phenomenon where models, despite initially providing correct answers, are persuaded by user-provided negations to reverse their outputs, often fabricating justifications. We conduct extensive evaluations of state-of-the-art MLLMs across diverse benchmarks and observe substantial performance drops when negation is introduced. Notably, we introduce the first benchmark GaslightingBench, specifically designed to evaluate the vulnerability of MLLMs to negation arguments. GaslightingBench consists of multiple-choice questions curated from existing datasets, along with generated negation prompts across 20 diverse categories. Throughout extensive evaluation, we find that proprietary models such as Gemini-1.5-flash and GPT-4o demonstrate better resilience compared to open-source counterparts like Qwen2-VL and LLaVA, though even advanced reasoning-oriented models like Gemini-2.5-Pro remain susceptible. Our category-level analysis further shows that subjective or socially nuanced domains (e.g., Social Relation, Image Emotion) are especially fragile, while more objective domains (e.g., Geography) exhibit relatively smaller but still notable drops. Overall, all evaluated MLLMs struggle to maintain logical consistency under gaslighting negation attack. These findings highlight a fundamental robustness gap and provide insights for developing more reliable and trustworthy multimodal AI systems. Project website: https://yxg1005.github.io/GaslightingNegationAttacks/.
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。