# Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models

arXiv: https://arxiv.org/abs/2511.16110 · HTML: https://mlsanity.com/paper/2511.16110/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2025.

## Built on by (most cited first, 2 of 2)

- [Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models](https://mlsanity.com/paper/2601.22737/) (2026)
- [A Comprehensive Review of One-Pixel Attack: Research Status, Taxonomy, Applications, Regulation Policy and Future Directions](https://mlsanity.com/paper/2610.00125/) (2026)

## Abstract (arXiv)

The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against adversarial attacks remains underexplored. We introduce Multi-Faceted Attack (MFA), a framework that systematically exposes general safety vulnerabilities in leading defense-equipped VLMs such as GPT-4o, Gemini-Pro, and Llama-4. The core component of MFA is the Attention-Transfer Attack (ATA), which hides harmful instructions inside a meta task with competing objectives. We provide a theoretical perspective based on reward hacking to explain why this attack succeeds. To improve cross-model transferability, we further introduce a lightweight transfer-enhancement algorithm combined with a simple repetition strategy that jointly bypasses both input-level and output-level filters without model-specific fine-tuning. Empirically, we show that adversarial images optimized for one vision encoder transfer broadly to unseen VLMs, indicating that shared visual representations create a cross-model safety vulnerability. Overall, MFA achieves a 58.5% success rate and consistently outperforms existing methods. On state-of-the-art commercial models, MFA reaches a 52.8% success rate, surpassing the second-best attack by 34%. These results challenge the perceived robustness of current defense mechanisms and highlight persistent safety weaknesses in modern VLMs. Code: https://github.com/cure-lab/MultiFacetedAttack