SPARTA：通过文本自编码器潜在空间中的黑盒对抗释义评估推理分割鲁棒性
SPARTA: Evaluating Reasoning Segmentation Robustness through Black-Box Adversarial Paraphrasing in Text Autoencoder Latent Space
AI总结：
针对推理分割模型的文本扰动鲁棒性研究不足的问题，提出黑盒对抗释义方法SPARTA，在文本自编码器潜在空间中以强化学习优化生成释义，在两个数据集上成功率较现有方法最高提升1倍，揭示先进模型仍易受此类攻击。
摘要：
多模态大语言模型（MLLMs）在推理分割等视觉-语言任务中展现出出色能力，这类任务中模型会根据文本查询生成分割掩码。此前研究主要聚焦于对图像输入施加扰动，而语义等价的文本释义——在用户以多种方式表达相同意图的真实应用中至关重要——仍未得到充分探索。为填补这一空白，我们提出一项新颖的对抗释义任务：生成语法正确、保留原查询含义同时降低分割性能的释义。为评估对抗释义的质量，我们开发了一套经人工研究验证的综合自动评估协议。此外，我们提出SPARTA——一种黑盒、句子级优化方法，在文本自编码器的低维语义潜在空间中运行，以强化学习为引导。SPARTA取得了显著更高的成功率，在ReasonSeg和LLMSeg-40k两个数据集上的表现均优于现有方法最高达2倍。我们利用SPARTA和主流基线评估了先进推理分割模型的鲁棒性，揭示出即使在严格的语义和语法约束下，这些模型仍易受对抗释义攻击。所有代码和数据将在论文录用后公开发布。
英文摘要：
Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation, where models generate segmentation masks based on textual queries. While prior work has primarily focused on perturbing image inputs, semantically equivalent textual paraphrases-crucial in real-world applications where users express the same intent in varied ways-remain underexplored. To address this gap, we introduce a novel adversarial paraphrasing task: generating grammatically correct paraphrases that preserve the original query meaning while degrading segmentation performance. To evaluate the quality of adversarial paraphrases, we develop a comprehensive automatic evaluation protocol validated with human studies. Furthermore, we introduce SPARTA-a black-box, sentence-level optimization method that operates in the low-dimensional semantic latent space of a text autoencoder, guided by reinforcement learning. SPARTA achieves significantly higher success rates, outperforming prior methods by up to 2x on both the ReasonSeg and LLMSeg-40k datasets. We use SPARTA and competitive baselines to assess the robustness of advanced reasoning segmentation models. We reveal that they remain vulnerable to adversarial paraphrasing-even under strict semantic and grammatical constraints. All code and data will be released publicly upon acceptance.
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。
