# Investigating Adversarial Robustness of Multi-modal Large Language Models

arXiv: https://arxiv.org/abs/2606.03713 · HTML: https://mlsanity.com/paper/2606.03713/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 58 of its 66 references that are in the map.
- First posted on arXiv 2 Jun 2026.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)

## Builds on (most cited first, 30 of 58)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering](https://mlsanity.com/paper/1612.00837/) (2016)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [A Survey on Multimodal Large Language Models](https://mlsanity.com/paper/2306.13549/) (2023)
- [VizWiz Grand Challenge: Answering Visual Questions from Blind People](https://mlsanity.com/paper/1802.08218/) (2018)
- [Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs](https://mlsanity.com/paper/2401.06209/) (2024)
- [DataComp: In search of the next generation of multimodal datasets](https://mlsanity.com/paper/2304.14108/) (2023)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models](https://mlsanity.com/paper/2308.01390/) (2023)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [Certified Robustness to Adversarial Examples with Differential Privacy](https://mlsanity.com/paper/1802.03471/) (2018)
- [Hallucination of Multimodal Large Language Models: A Survey](https://mlsanity.com/paper/2404.18930/) (2024)
- [Using Pre-Training Can Improve Model Robustness and Uncertainty](https://mlsanity.com/paper/1901.09960/) (2019)

## Abstract (arXiv)

Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e.g., CLIP) substantially expands the attack surface, making these models vulnerable to visual adversarial perturbations. Prior defenses typically preserve compatibility with pretrained MLLMs by enforcing strict alignment to CLIP's original embedding space during adversarial fine-tuning; while practical, this constraint fundamentally limits achievable robustness. We present a systematic investigation of adversarial robustness in MLLMs. We first introduce a diagnostic CLIP-alignment protocol that predicts, prior to full MLLM training, which robust vision encoders will transfer effectively to the multimodal setting, revealing that large-scale multimodal adversarial pretraining, rather than unimodal scale alone, is the critical factor for strong robustness transfer. Integrating such encoders into MLLMs via end-to-end multimodal training yields average gains of 28 CIDEr points on captioning and 11.7% VQA accuracy under strong adversarial attacks compared to constrained plug-and-play baselines. We further show that adversarial training applied directly to a standard non-robust MLLM degrades both clean and adversarial performance, establishing robust visual representations as a strict prerequisite, while end-to-end adversarial training from a robust backbone delivers additional gains of 1.9 CIDEr points and 4.3% VQA accuracy. Beyond training-time defenses, lightweight test-time visual stochastic transformations serve as an effective black-box defense for non-robust MLLMs, elevating adversarial performance from near-zero to levels comparable with robust models. Finally, we show that our robust models substantially reduce toxic generation under white-box visual jailbreak attacks. Code and pretrained weights will be released publicly.