.png){kind=icon}
返回
Backpack: A Backpropagable Adversarial Embedding Scheme
.png){kind=icon}
OA
AI
DOI：10.1109/TIFS.2022.3204218.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
Protocols
Detectors
Games
Costs
Steganography
Security
Distortion
Steganography
steganalysis
distortion function
adversarial attacks
期刊
IF:
8
论文数:
5.2K
被引数:
2.3W
机构
引用论文
.png){kind=icon}
分享收藏Homeless Interactions with the Built Environment: A Spatial Pattern Language of Abandoned Housing
OAAI
OAAI分享收藏
查看更多内容