Metraipolis › archive › dc_e27211f529aa
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards — arXiv:2608.07535
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.07535
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T08:55:05.280Z
- SHA-256 of the archived text
5e56f035f34e087284f338a6f9e6fae3b85ea7ad0e91497d83c7e4b39ff2dede- Stable URL of this page
https://metraipolis.com/documento/dc_e27211f529aa
How to cite
Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards — arXiv:2608.07535 — arXiv (en), https://arxiv.org/abs/2608.07535 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e27211f529aa (Metraipolis archive dc_e27211f529aa, sha256 5e56f035f34e087284f338a6f9e6fae3b85ea7ad0e91497d83c7e4b39ff2dede)
BibTeX
@misc{dce27211f529aa,
title = {Evolving Safety Landscape of Multi-modal Large Language Models: A Survey of Emerging Threats and Safeguards — arXiv:2608.07535},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.07535},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e27211f529aa; sha256 5e56f035f34e087284f338a6f9e6fae3b85ea7ad0e91497d83c7e4b39ff2dede},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07535. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this architectural shift reshapes the safety landscape of machine learning. Increased model complexity and cross-modal interactions give rise to novel threats, including compromised modality integration, modality misalignment, and fused safety risks, reflecting shifts in threat modeling beyond uni-modal assumptions. These shifts, in turn, impose new constraints on safety solutions not captured by existing frameworks rooted in uni-modal learning. Motivated by these challenges, this survey provides a systematic analysis of the evolving safety landscape of MLLMs. We first propose a multimodal grounded taxonomy of safety threats and analyze shifts in threat models, covering adversarial attacks, data poisoning, jailbreaks, and hallucinations. We then summarize updated safety assumptions and organize recent advances in MLLM safety strategies accordingly. Finally, we discuss open challenges and future directions to inform the development of more principled and scalable safety mechanisms for multimodal systems. Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CY). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY). Pagina del lavoro: https://arxiv.org/abs/2608.07535 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T08:51:53.759Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).