mlsanityData to 14 Oct 2026

A Framework for Evaluating Vision-Language Model Safety: Building Trust in AI for Public Sector Applications

arXiv 2502.16361 ↗First posted 22 Feb 2025cs.CY cs.CL cs.CVcited by 1

On the map: Multimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness

Abstract (arXiv)

Vision-Language Models (VLMs) are increasingly deployed in public sector missions, necessitating robust evaluation of their safety and vulnerability to adversarial attacks. This paper introduces a novel framework to quantify adversarial risks in VLMs. We analyze model performance under Gaussian, salt-and-pepper, and uniform noise, identifying misclassification thresholds and deriving composite noise patches and saliency patterns that highlight vulnerable regions. These patterns are compared against the Fast Gradient Sign Method (FGSM) to assess their adversarial effectiveness. We propose a new Vulnerability Score that combines the impact of random noise and adversarial attacks, providing a comprehensive metric for evaluating model robustness.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 8 of its 13 references that are in the map. First posted on arXiv 22 Feb 2025.

Builds on

8 of 13 references.

References · 8

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  6. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  7. 2018Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approachcited by 182
  8. 2024AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioningcited by 3

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025VSF-Med:A Vulnerability Scoring Framework for Medical Vision-Language Modelscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques
  2. 2025A Survey of Safety on Large Vision-Language Models: Attacks, Defenses and Evaluations
  3. 2024A Hybrid Defense Strategy for Boosting Adversarial Robustness in Vision-Language Models
  4. 2025Safeguarding Vision-Language Models: Mitigating Vulnerabilities to Gaussian Noise in Perturbation-based Attacks
  5. 2024Retention Score: Quantifying Jailbreak Risks for Vision Language Models
  6. 2023On Evaluating Adversarial Robustness of Large Vision-Language Models
  7. 2026Adversarial attacks against Modern Vision-Language Models
  8. 2023How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs