From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866915991724752896 |
|---|---|
| author | Han, Jiaju Li, Chao Hu, Chengyin Zhang, Qike Sun, Xuemeng Wang, Xin Zhang, Fengyu Chen, Xiang Wei, Yiwei Long, Jiahuan Guo, Jiujiang |
| author_facet | Han, Jiaju Li, Chao Hu, Chengyin Zhang, Qike Sun, Xuemeng Wang, Xin Zhang, Fengyu Chen, Xiang Wei, Yiwei Long, Jiahuan Guo, Jiujiang |
| contents | Multimodal RAG systems increasingly rely on vision-language retrievers to ground visual queries in external textual evidence. Existing adversarial studies on RAG mainly manipulate the retrieval corpus or memory, while attacks on vision-language and remote sensing models typically target end-task predictions. Input-space threats to the evidence retrieval stage of remote sensing multimodal RAG remain underexplored. To address this gap, we introduce CloudWeb, an atmospheric retrieval hijacking attack that modifies only the input image while keeping the retriever, generator, and knowledge base fixed at deployment. CloudWeb overlays parameterized cloud- and haze-like patterns on remote sensing images and optimizes them with a retrieval-oriented objective that pulls adversarial image embeddings toward target atmospheric evidence, suppresses source-scene evidence, enforces rank separation, and regularizes naturalness and coverage. To the best of our knowledge, this is the first study of retrieval-stage atmospheric evidence hijacking in remote sensing multimodal RAG. We evaluate CloudWeb on a seven-dataset remote sensing RAG benchmark with five CLIP-style retrievers, including GeoRSCLIP, RemoteCLIP, OpenAI CLIP, and OpenCLIP, together with downstream vision-language generators. Across retrievers, CloudWeb consistently outperforms clean retrieval, handcrafted atmospheric baselines, random cloud perturbations, and fixed variants in injecting weather-related evidence into top-ranked results. On GeoRSCLIP ViT-B/32, Weather@5 increases from 0.71\% to 43.29\%. Downstream generation further shows measurable weather hallucination and semantic shift, indicating that retrieval-stage hijacking can propagate to the final RAG response. These findings reveal a practical failure mode: natural-looking atmospheric changes can compromise evidence retrieval before generation begins. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_07273 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG Han, Jiaju Li, Chao Hu, Chengyin Zhang, Qike Sun, Xuemeng Wang, Xin Zhang, Fengyu Chen, Xiang Wei, Yiwei Long, Jiahuan Guo, Jiujiang Computer Vision and Pattern Recognition Artificial Intelligence Multimodal RAG systems increasingly rely on vision-language retrievers to ground visual queries in external textual evidence. Existing adversarial studies on RAG mainly manipulate the retrieval corpus or memory, while attacks on vision-language and remote sensing models typically target end-task predictions. Input-space threats to the evidence retrieval stage of remote sensing multimodal RAG remain underexplored. To address this gap, we introduce CloudWeb, an atmospheric retrieval hijacking attack that modifies only the input image while keeping the retriever, generator, and knowledge base fixed at deployment. CloudWeb overlays parameterized cloud- and haze-like patterns on remote sensing images and optimizes them with a retrieval-oriented objective that pulls adversarial image embeddings toward target atmospheric evidence, suppresses source-scene evidence, enforces rank separation, and regularizes naturalness and coverage. To the best of our knowledge, this is the first study of retrieval-stage atmospheric evidence hijacking in remote sensing multimodal RAG. We evaluate CloudWeb on a seven-dataset remote sensing RAG benchmark with five CLIP-style retrievers, including GeoRSCLIP, RemoteCLIP, OpenAI CLIP, and OpenCLIP, together with downstream vision-language generators. Across retrievers, CloudWeb consistently outperforms clean retrieval, handcrafted atmospheric baselines, random cloud perturbations, and fixed variants in injecting weather-related evidence into top-ranked results. On GeoRSCLIP ViT-B/32, Weather@5 increases from 0.71\% to 43.29\%. Downstream generation further shows measurable weather hallucination and semantic shift, indicating that retrieval-stage hijacking can propagate to the final RAG response. These findings reveal a practical failure mode: natural-looking atmospheric changes can compromise evidence retrieval before generation begins. |
| title | From Clouds to Hallucinations: Atmospheric Retrieval Hijacking in Remote Sensing Vision-Language RAG |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2605.07273 |