Investigating Adversarial Robustness of Multi-modal Large Language Models

• URL: http://arxiv.org/abs/2606.03713v1
• Date: Tue, 02 Jun 2026 14:34:48 GMT
• Title: Investigating Adversarial Robustness of Multi-modal Large Language Models
• Abstract summary: Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks.<n>But incorporating visual inputs through a vision encoder (e.g., CLIP) substantially expands the attack surface.<n>We present a systematic investigation of adversarial robustness in MLLMs.
• Score: 37.24612885977265
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Breaking the weakest link to evade vision language models [0.254890465057467]
  Vision Language Models (VLMs) have emerged as a critical component of multimodal AI systems.<n>In this work, we investigate the vulnerability of VLMs to adversarial perturbations applied to visual inputs.<n>We show that small, human-imperceptible perturbations can substantially alter the textual interpretation produced by the models.
  arXiv  Detail & Related papers  (2026-08-19T14:06:31Z)
• Dual Adversarial Fine-tuning for Enhancing Robustness of Large Vision Language Model [73.59026525350808]
  We propose a dual adversarial fine-tuning framework that jointly optimize visual and semantic supervision signals from two modalities.<n>Our approach outperforms the state-of-the-art method in adversarial robustness evaluation across zero-shot classification, image captioning, and visual question answering tasks.
  arXiv  Detail & Related papers  (2026-07-21T10:49:29Z)
• Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models [67.45032003041399]
  We propose a novel Multi-Paradigm Collaborative Attack (MPCAttack) framework to boost the transferability of adversarial examples against MLLMs.<n>MPCO adaptively balances the importance of different paradigm representations and guides the global optimisation.<n>Our solution consistently outperforms state-of-the-art methods in both targeted and untargeted attacks on open-source and closed-source MLLMs.
  arXiv  Detail & Related papers  (2026-03-05T06:01:26Z)
• To Deceive is to Teach? Forging Perceptual Robustness via Adversarial Reinforcement Learning [6.973386095391195]
  We introduce textbfAOT (Adversarial Opponent Training), a self-play framework that forges MLLM robustness by creating its own training data.<n>Our method orchestrates a co-evolution between an image-editing Attacker and a Defender MLLM, where the Attacker generates a diverse and dynamic curriculum of image manipulations, forcing the Defender to adapt and improve.
  arXiv  Detail & Related papers  (2026-01-24T03:47:29Z)
• Universal Camouflage Attack on Vision-Language Models for Autonomous Driving [67.34987318443761]
  Visual language modeling for automated driving is emerging as a promising research direction.<n>VLM-AD remains vulnerable to serious security threats from adversarial attacks.<n>We propose the first Universal Camouflage Attack framework for VLM-AD.
  arXiv  Detail & Related papers  (2025-09-24T14:52:01Z)
• Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks [17.75247947379804]
  We present the first adversarial training paradigm tailored to defend against jailbreak attacks during the MLLM training phase.<n>We introduce Projection Layer Against Adversarial Training (ProEAT), an end-to-end AT framework.<n>ProEAT achieves state-of-the-art defense performance, outperforming existing baselines by an average margin of +34% across text and image modalities.
  arXiv  Detail & Related papers  (2025-03-05T14:13:35Z)
• Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models [26.656858396343726]
  Multi-modal Large Language Models (MLLMs) excel in vision-language tasks but remain vulnerable to visual adversarial perturbations.<n>Existing methods seek to mitigate these risks by applying constrained adversarial fine-tuning to CLIP vision encoders on ImageNet-scale data.<n>We explore an alternative approach of leveraging existing vision classification models that have been adversarially pre-trained on large-scale data.
  arXiv  Detail & Related papers  (2025-02-03T17:59:45Z)
• Efficient Adversarial Training in LLMs with Continuous Attacks [99.5882845458567]
  Large language models (LLMs) are vulnerable to adversarial attacks that can bypass their safety guardrails. We propose a fast adversarial training algorithm (C-AdvUL) composed of two losses. C-AdvIPO is an adversarial variant of IPO that does not require utility data for adversarially robust alignment.
  arXiv  Detail & Related papers  (2024-05-24T14:20:09Z)
• On Evaluating Adversarial Robustness of Large Vision-Language Models [64.66104342002882]
  We evaluate the robustness of large vision-language models (VLMs) in the most realistic and high-risk setting. In particular, we first craft targeted adversarial examples against pretrained models such as CLIP and BLIP. Black-box queries on these VLMs can further improve the effectiveness of targeted evasion.
  arXiv  Detail & Related papers  (2023-05-26T13:49:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.