# A Semantic Decoupling-Based Two-Stage Rainy-Day Attack for Revealing Weather Robustness Deficiencies in Vision-Language Models

arXiv: https://arxiv.org/abs/2601.13238 · HTML: https://mlsanity.com/paper/2601.13238/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 16 of its 37 references that are in the map.
- First posted on arXiv 19 Jan 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [EfficientNetV2: Smaller Models and Faster Training](https://mlsanity.com/paper/2104.00298/) (2021)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks](https://mlsanity.com/paper/2406.18403/) (2024)
- [Shadows can be Dangerous: Stealthy and Effective Physical-world Adversarial Attack by Natural Phenomenon](https://mlsanity.com/paper/2203.03818/) (2022)
- [Fine-Grained Semantically Aligned Vision-Language Pre-Training](https://mlsanity.com/paper/2208.02515/) (2022)
- [Analysing the Robustness of Vision-Language-Models to Common Corruptions](https://mlsanity.com/paper/2504.13690/) (2025)
- [cmaes: A Simple yet Practical Python Library for CMA-ES](https://mlsanity.com/paper/2402.01373/) (2024)
- [AdvDreamer Unveils: Are Vision-Language Models Truly Ready for Real-World 3D Variations?](https://mlsanity.com/paper/2412.03002/) (2024)

## Built on by (most cited first, 1 of 1)

- [Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?](https://mlsanity.com/paper/2606.08063/) (2026)

## Abstract (arXiv)

Vision-Language Models (VLMs) are trained on image-text pairs collected under canonical visual conditions and achieve strong performance on multimodal tasks. However, their robustness to real-world weather conditions, and the stability of cross-modal semantic alignment under such structured perturbations, remain insufficiently studied. In this paper, we focus on rainy scenarios and introduce the first adversarial framework that exploits realistic weather to attack VLMs, using a two-stage, parameterized perturbation model based on semantic decoupling to analyze rain-induced shifts in decision-making. In Stage 1, we model the global effects of rainfall by applying a low-dimensional global modulation to condition the embedding space and gradually weaken the original semantic decision boundaries. In Stage 2, we introduce structured rain variations by explicitly modeling multi-scale raindrop appearance and rainfall-induced illumination changes, and optimize the resulting non-differentiable weather space to induce stable semantic shifts. Operating in a non-pixel parameter space, our framework generates perturbations that are both physically grounded and interpretable. Experiments across multiple tasks show that even physically plausible, highly constrained weather perturbations can induce substantial semantic misalignment in mainstream VLMs, posing potential safety and reliability risks in real-world deployment. Ablations further confirm that illumination modeling and multi-scale raindrop structures are key drivers of these semantic shifts.