Adversarial Framing for Image and Video Classification
| العنوان: | Adversarial Framing for Image and Video Classification |
|---|---|
| المؤلفون: | Konrad Zolna, Negar Rostamzadeh, Michal Zajac, Pedro O. Pinheiro |
| المصدر: | AAAI |
| بيانات النشر: | Association for the Advancement of Artificial Intelligence (AAAI), 2019. |
| سنة النشر: | 2019 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Computer Science - Machine Learning, Framing (visual arts), Source code, Pixel, Artificial neural network, Computer Science - Artificial Intelligence, business.industry, Computer science, Computer Vision and Pattern Recognition (cs.CV), media_common.quotation_subject, Computer Science - Computer Vision and Pattern Recognition, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Machine Learning (stat.ML), General Medicine, Machine Learning (cs.LG), Adversarial system, Artificial Intelligence (cs.AI), Statistics - Machine Learning, Computer vision, Artificial intelligence, business, media_common |
| الوصف: | Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps the image unchanged and only adds an adversarial framing on the border of the image. We show empirically that our method is able to successfully attack state-of-the-art methods on both image and video classification problems. Notably, the proposed method results in a universal attack which is very fast at test time. Source code can be found at https://github.com/zajaczajac/adv_framing . This is an extended version of the paper published at 33rd AAAI Conference on Artificial Intelligence (see https://doi.org/10.1609/aaai.v33i01.330110077 ) |
| تدمد: | 2374-3468 2159-5399 |
| URL الوصول: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::10554dc57c353af2965c504815d7aa1f https://doi.org/10.1609/aaai.v33i01.330110077 |
| حقوق: | OPEN |
| رقم الأكسشن: | edsair.doi.dedup.....10554dc57c353af2965c504815d7aa1f |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 23743468 21595399 |
|---|