الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Recently, Vision-Language-Action (VLA) models have revolutionized robotic manipulation by seamlessly integrating visual perception, language understanding, and action generation in an end-to-end learning framework. However, since these models are designed to interact directly with the physical world and humans, their security is critical, and even small vulnerabilities can lead to catastrophic failures. In this work, we propose the Universal Adversarial Object, a sphere with optimized surface texture that significantly degrades task success rates when placed within the robot's field of view. Specifically, our approach introduces a multi-level attack framework that jointly disrupts trajectory planning, task execution, and action control. We validate our method in both simulated and real-world robotic settings. Experimental results demonstrate that the adversarial object reduces the average task success rates by 31.2%-39.9% for two representative VLA models (Pi0 and RDT), with success rates dropping to near zero in complex scenarios. Index Terms--Vision-Language-Action models, adversarial attack, robotic security, universal adversarial object
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Yang, S., Liu, Z., Liu, Y., Li, X., Fei, X., Huang, H., Wang, Z., & Li, M. (2026). استغلال الثغرات: هجمات عدائية شاملة على نماذج الرؤية واللغة والفعل في الروبوتات. https://omanscience.com/ar/articles/exploiting-vulnerabilities-universal-adversarial-attacks-on-vision-language-action-models-in-robotics
MLA 9
Yang, Songhua, et al. "استغلال الثغرات: هجمات عدائية شاملة على نماذج الرؤية واللغة والفعل في الروبوتات." https://omanscience.com/ar/articles/exploiting-vulnerabilities-universal-adversarial-attacks-on-vision-language-action-models-in-robotics.
شيكاغو (المؤلف–التاريخ)
Yang, Songhua, Ziyu Liu, Yuanwei Liu, Xuetao Li, Xuanye Fei, He Huang, Zheng Wang, and Miao Li. 2026. "استغلال الثغرات: هجمات عدائية شاملة على نماذج الرؤية واللغة والفعل في الروبوتات." https://omanscience.com/ar/articles/exploiting-vulnerabilities-universal-adversarial-attacks-on-vision-language-action-models-in-robotics.
هارفارد
Yang, S., Liu, Z., Liu, Y., Li, X., Fei, X., Huang, H., Wang, Z. and Li, M. (2026) 'استغلال الثغرات: هجمات عدائية شاملة على نماذج الرؤية واللغة والفعل في الروبوتات', Available at: https://omanscience.com/ar/articles/exploiting-vulnerabilities-universal-adversarial-attacks-on-vision-language-action-models-in-robotics.
فانكوفر
Yang S, Liu Z, Liu Y, Li X, Fei X, Huang H, et al. استغلال الثغرات: هجمات عدائية شاملة على نماذج الرؤية واللغة والفعل في الروبوتات. https://omanscience.com/ar/articles/exploiting-vulnerabilities-universal-adversarial-attacks-on-vision-language-action-models-in-robotics
IEEE
S. Yang, Z. Liu, Y. Liu, X. Li, X. Fei, H. Huang, Z. Wang, and M. Li, "استغلال الثغرات: هجمات عدائية شاملة على نماذج الرؤية واللغة والفعل في الروبوتات," https://omanscience.com/ar/articles/exploiting-vulnerabilities-universal-adversarial-attacks-on-vision-language-action-models-in-robotics.