4.7 Article

Backpack: A Backpropagable Adversarial Embedding Scheme

期刊

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIFS.2022.3204218

关键词

Protocols; Detectors; Games; Costs; Steganography; Security; Distortion; Steganography; steganalysis; distortion function; adversarial attacks

资金

  1. French National Research Agency [ANR-18-ASTR-0009]
  2. ALASKA Project
  3. French ANR DEFALS Program [ANR-16-DEFA-0003]
  4. Research Center for Informatics, OP VVV Project [CZ.02.1.01/0.0/0.0/16_019/0000765]
  5. Czech Ministry of Education [19-29680L]
  6. Grand Equipement National de Calcul Intensif (GENCI) [2019-AD011011259, 2022-AD011012567R1]
  7. Agence Nationale de la Recherche (ANR) [ANR-18-ASTR-0009] Funding Source: Agence Nationale de la Recherche (ANR)

向作者/读者索取更多资源

The minmax protocol automatically optimizes steganographic algorithms against various steganalytic detectors, while Backpack provides a theoretically sound solution to address the flaws in the protocol. Experimental verification shows that Backpack performs better than ADV-EMB and enhances the security of steganographic algorithms.
A minmax protocol offers a general method to automatically optimize steganographic algorithm against a wide class of steganalytic detectors. The quality of the resulting steganograhic algorithm depends on the ability to find an adversarial stego image undetectable by a set of detectors while communicating a given message. Despite minmax protocol instantiated with ADV-EMB scheme leading to unexpectedly good results, we show it suffers a significant flaw and we present a theoretically sound solution called Backpack. Extensive experimental verification of minmax protocol with Backpack shows superior performance to ADV-EMB, the generality of the tool by targeting a new JPEG QF100 compatibility attack and further improves the security of steganographic algorithms.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据