Paper Review/Vision Language Model (VLM)(6)
-
[컬럼리뷰] A Dive into Vision-Language Models
벌써 1월, 아니 2월, 아니 3월입니다.2025년을 너무 정신 없이 살다보니 블로그 글 업데이트는 계속 늦어졌네요.오늘은 토마토에게 한소리 듣고 작성해보는 Vision Language Model (VLM) 리뷰입니다.VLM 관련 연구를 하면서 정작 VLM에 대해서는 돌아보지 않는다구 박.. 은 아니고 뭐 그렇습니다. 이번에 리뷰할 글은 논문은 아니고 허깅페이스에 올라온 컬럼(?)입니다.https://huggingface.co/blog/vision_language_pretraining#supporting-vision-language-models-in-%F0%9F%A4%97-transformers A Dive into Vision-Language Models huggingface.coVLM 모델을 가볍게 ..
2025.03.12 -
[데이터셋리뷰] JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks
Luo, W., Ma, S., Liu, X., Guo, X., & Xiao, C. (2024). JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks. https://arxiv.org/abs/2404.03027 JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak AttacksWith the rapid advancements in Multimodal Large Language Models (MLLMs), securing..
2025.01.06 -
[논문리뷰] Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey
Liu, X., Cui, X., Li, P., Li, Z., Huang, H., Xia, S., Zhang, M., Zou, Y., & He, R. (2024). Jailbreak Attacks and Defenses against Multimodal Generative Models: A Survey. https://arxiv.org/abs/2411.09259 Jailbreak Attacks and Defenses against Multimodal Generative Models: A SurveyThe rapid evolution of multimodal foundation models has led to significant advancements in cross-modal understanding a..
2024.12.31 -
[논문리뷰] BLUE SUFFIX: REINFORCED BLUE TEAMING FOR VISION-LANGUAGE MODELS AGAINST JAILBREAK ATTACKS
Zhao, Y., Zheng, X., Luo, L., Li, Y., Ma, X., & Jiang, Y. (2024). BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak Attacks. ArXiv, abs/2410.20971.https://arxiv.org/abs/2410.20971 BlueSuffix: Reinforced Blue Teaming for Vision-Language Models Against Jailbreak AttacksDespite their superb multimodal capabilities, Vision-Language Models (VLMs) have been shown to be v..
2024.12.30 -
[논문리뷰] White-box Multimodal Jailbreaks Against Large Vision-Language Models
Wang, R., Ma, X., Zhou, H., Ji, C., Ye, G., & Jiang, Y. (2024). White-box Multimodal Jailbreaks Against Large Vision-Language Models. ACM Multimedia.https://arxiv.org/abs/2405.17894 White-box Multimodal Jailbreaks Against Large Vision-Language ModelsRecent advancements in Large Vision-Language Models (VLMs) have underscored their superiority in various multimodal tasks. However, the adversarial ..
2024.12.27 -
[논문리뷰] Visual Adversarial Examples Jailbreak Aligned Large Language Models
Qi, X., Huang, K., Panda, A., Henderson, P., Wang, M., & Mittal, P. (2024). Visual Adversarial Examples Jailbreak Aligned Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, 38(19), 21527-21536. https://doi.org/10.1609/aaai.v38i19.30150 https://arxiv.org/abs/2306.13213 Visual Adversarial Examples Jailbreak Aligned Large Language ModelsRecently, there has been a ..
2024.12.26