# RLBind: Adversarial-Invariant Cross-Modal Alignment for Unified Robust Embeddings

arXiv: https://arxiv.org/abs/2509.14383 · HTML: https://mlsanity.com/paper/2509.14383/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 22 references that are in the map.
- First posted on arXiv 17 Sep 2025.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment](https://mlsanity.com/paper/2310.01852/) (2023)
- [LLVIP: A Visible-infrared Paired Dataset for Low-light Vision](https://mlsanity.com/paper/2108.10831/) (2021)
- [Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions](https://mlsanity.com/paper/2111.10337/) (2021)
- [Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling](https://mlsanity.com/paper/2307.14126/) (2023)
- [Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models](https://mlsanity.com/paper/2402.12336/) (2024)
- [Understanding Zero-Shot Adversarial Robustness for Large-Scale Models](https://mlsanity.com/paper/2212.07016/) (2022)
- [Deep Multimodal Learning with Missing Modality: A Survey](https://mlsanity.com/paper/2409.07825/) (2024)
- [UniBind: LLM-Augmented Unified and Balanced Representation Space to Bind Them All](https://mlsanity.com/paper/2403.12532/) (2024)
- [Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation](https://mlsanity.com/paper/2310.03986/) (2023)
- [Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective](https://mlsanity.com/paper/2404.19287/) (2024)
- [Enhance Modality Robustness in Text-Centric Multimodal Alignment with Adversarial Prompting](https://mlsanity.com/paper/2408.09798/) (2024)

## Abstract (arXiv)

Unified multi-modal encoders that bind vision, audio, and other sensors into a shared embedding space are attractive building blocks for robot perception and decision-making. However, on-robot deployment exposes the vision branch to adversarial and natural corruptions, making robustness a prerequisite for safety. Prior defenses typically align clean and adversarial features within CLIP-style encoders and overlook broader cross-modal correspondence, yielding modest gains and often degrading zero-shot transfer. We introduce RLBind, a two-stage adversarial-invariant cross-modal alignment framework for robust unified embeddings. Stage 1 performs unsupervised fine-tuning on clean-adversarial pairs to harden the visual encoder. Stage 2 leverages cross-modal correspondence by minimizing the discrepancy between clean/adversarial features and a text anchor, while enforcing class-wise distributional alignment across modalities. Extensive experiments on Image, Audio, Thermal, and Video data show that RLBind consistently outperforms the LanguageBind backbone and standard fine-tuning baselines in both clean accuracy and norm-bounded adversarial robustness. By improving resilience without sacrificing generalization, RLBind provides a practical path toward safer multi-sensor perception stacks for embodied robots in navigation, manipulation, and other autonomy settings.