The paper demonstrates that a targeted adversarial perturbation can reduce a vision‑language model’s training loss to near zero for a fixed target caption, yet the same model, when generating freely, still produces the correct description. This phenomenon, termed the train/inference gap, is traced to a single autoregressive step where the target token’s rank is fixed across all images, and further analysis shows that the language decoder, rather than the visual encoder, determines whether the corrupted signal is amplified or suppressed. The study uses a controlled two‑stage PGD attack on Qwen2.5‑VL‑7B‑Instruct and evaluates the effect on 200 held‑out COCO images, revealing that adversarial robustness in autoregressive VLMs largely depends on the language decoder’s prior. whyItMatters":"The findings suggest that defenses and faithfulness evaluations for deployed vision‑language models should focus on the language decoder rather than the visual encoder, as the former is the key determinant of robustness to adversarial perturbations."
arXiv:2506. 03933v2 Announce Type: replace-cross Abstract: Vision Language Models (VLMs) have shown remarkable capabilities in multimodal understanding, yet their susceptibility to adversarial perturbations poses a significant threat to their reliability in real-world applications.
arXiv:2609.39134v1 Announce Type: new Abstract: Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study a...
Multi-modal Large Language Models (MLLMs) achieve strong performance on vision-language tasks, but incorporating visual inputs through a vision encoder (e. g.
arXiv:2606. 10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness.
arXiv:2606. 07593v1 Announce Type: cross Abstract: The widespread use of image classification models in high-risk, real-world situations necessitates making these models robust to slight disturbances or perturbations, such as blurring or sharpening, in the input images.
arXiv:2609.05889v1 Announce Type: new Abstract: Resource-exhaustion attacks against autoregressive vision-language models (VLMs) typically assume unimodal threat models, treating the image branch as...
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...
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.
arXiv:2608. 06674v1 Announce Type: cross Abstract: Adversarial vulnerabilities remain a major concern for the safe deployment of neural networks, particularly in object detection, a core task embedded in many safety-critical systems.
arXiv:2607. 26993v1 Announce Type: new Abstract: Face presentation attack detection (PAD) remains challenging under cross-dataset evaluation, where domain shift degrades models trained on a single dataset.
arXiv:2608. 01043v2 Announce Type: replace-cross Abstract: We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR).
arXiv:2609.38298v1 Announce Type: new Abstract: Vision Language Models (VLMs) are widely deployed in safety-critical scenarios, and understanding to which extent they can be controlled by adversarial...