arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
The paper investigates how Vision Language Models (VLMs) can be fooled by small, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal alignment. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these perturbations can significantly alter the models’ textual outputs.
The paper investigates how Vision Language Models (VLMs) can be fooled by tiny, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal interpretations. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these small perturbations can dramatically alter the models’ textual outputs.
While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks. Existing defense methods predominantly target single-task scenarios (e.
arXiv:2607. 18958v1 Announce Type: cross Abstract: While Large Vision-Language Models (LVLMs), represented by LLaVA and GPT-4V, have demonstrated remarkable capabilities, their visual inputs remain vulnerable to adversarial attacks, posing significant security risks.
arXiv:2406. 09250v5 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are increasingly susceptible to sophisticated adversarial attacks, including adaptive strategies specifically designed to bypass existing defenses.
arXiv:2602.08136v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic...
arXiv:2606. 24388v1 Announce Type: new Abstract: We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs).
The paper introduces Inverse Knowledge Distillation (IKD), an attack‑agnostic technique that enhances adversarial transferability by maximizing the discrepancy between benign and adversarial prediction distributions on a surrogate model. IKD employs a CE/KL‑equivalent soft‑label objective to push adversarial predictions away from a fixed benign anchor, leveraging Fisher‑sensitive surrogate directions. The authors provide theoretical analysis showing CE and KL induce identical gradients, derive a lower bound on Fisher‑subspace overlap, and demonstrate through extensive ImageNet experiments that IKD consistently improves black‑box attack performance across CNN, ViT, and defended models.
arXiv:2607. 09450v1 Announce Type: cross Abstract: Pre-trained Vision-Language Models (VLMs) such as CLIP achieve strong zero-shot generalization, but their performance degrades sharply under adversarial perturbations.
arXiv:2607. 07922v1 Announce Type: cross Abstract: Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.
arXiv:2605. 25194v2 Announce Type: replace Abstract: Adversarial images pose a severe security threat to multimodal large language models through prompt injection.