الملخص
تمت ترجمة أجزاء من هذه الصفحة آلياً وقد تحتوي على أخطاء.
Adversarial attacks have long posed a fundamental threat to machine learning systems. As multimodal large language models (MLLMs) rapidly evolve and become widely deployed, assessing their vulnerability to such attacks is essential for their safe use. In this work, we investigate whether a single adversarial image can consistently mislead diverse frontier MLLMs in black-box settings. We propose O-Attack, a highly transferable black-box attack framework. This framework builds on our insight that surrogate models contain a broad, high-level, cross-modally aligned semantic space. This space extends beyond final-layer outputs and provides multiple semantically consistent representations that remain underexploited by existing attacks. Within this space, O-Attack anchors aligned representations, progressively broadens semantic conditions, and optimizes perturbations through semantic consensus to promote consistent target alignment. By fully exploiting this space with the same surrogate models as M-Attack, O-Attack raises attack success rates on GPT-5.4 (29.1% to 77.2%), Claude-4.6 (42.8% to 81.6%), and Gemini-3.1 (38.2% to 80.9%). Extensive experiments across 24 MLLMs show that O-Attack outperforms six state-of-the-art methods in black-box transferability, with consistent effectiveness across prompts and improved efficiency and imperceptibility. This work exposes the practical safety risks posed by black-box adversarial attacks against frontier MLLMs, underscoring the need for more rigorous robustness evaluation and more effective defenses.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Nie, S., Zhang, J., Wang, Z., Shan, S., & Chen, X. (2026). هجوم واحد يخدع الجميع: هجمات عدائية صندوقية سوداء قابلة للنقل بدرجة عالية على نماذج MLLM المتقدمة. https://omanscience.com/ar/articles/one-attack-to-fool-them-all-highly-transferable-black-box-adversarial-attacks-on-frontier-mllms
MLA 9
Nie, Sen, et al. "هجوم واحد يخدع الجميع: هجمات عدائية صندوقية سوداء قابلة للنقل بدرجة عالية على نماذج MLLM المتقدمة." https://omanscience.com/ar/articles/one-attack-to-fool-them-all-highly-transferable-black-box-adversarial-attacks-on-frontier-mllms.
شيكاغو (المؤلف–التاريخ)
Nie, Sen, Jie Zhang, Zhongqi Wang, Shiguang Shan, and Xilin Chen. 2026. "هجوم واحد يخدع الجميع: هجمات عدائية صندوقية سوداء قابلة للنقل بدرجة عالية على نماذج MLLM المتقدمة." https://omanscience.com/ar/articles/one-attack-to-fool-them-all-highly-transferable-black-box-adversarial-attacks-on-frontier-mllms.
هارفارد
Nie, S., Zhang, J., Wang, Z., Shan, S. and Chen, X. (2026) 'هجوم واحد يخدع الجميع: هجمات عدائية صندوقية سوداء قابلة للنقل بدرجة عالية على نماذج MLLM المتقدمة', Available at: https://omanscience.com/ar/articles/one-attack-to-fool-them-all-highly-transferable-black-box-adversarial-attacks-on-frontier-mllms.
فانكوفر
Nie S, Zhang J, Wang Z, Shan S, Chen X. هجوم واحد يخدع الجميع: هجمات عدائية صندوقية سوداء قابلة للنقل بدرجة عالية على نماذج MLLM المتقدمة. https://omanscience.com/ar/articles/one-attack-to-fool-them-all-highly-transferable-black-box-adversarial-attacks-on-frontier-mllms
IEEE
S. Nie, J. Zhang, Z. Wang, S. Shan, and X. Chen, "هجوم واحد يخدع الجميع: هجمات عدائية صندوقية سوداء قابلة للنقل بدرجة عالية على نماذج MLLM المتقدمة," https://omanscience.com/ar/articles/one-attack-to-fool-them-all-highly-transferable-black-box-adversarial-attacks-on-frontier-mllms.