Sorry, you need to enable JavaScript to visit this website.

IMAGE STEGANOGRAPHY BASED ON ITERATIVE ADVERSARIAL PERTURBATIONS ONTO A SYNCHRONIZED-DIRECTIONS SUB-IMAGE

Citation Author(s):
Xinghong Qin, Shunquan Tan, Weixuan Tang, Bin Li, Jiwu Huang
Submitted by:
Xinghong Qin
Last updated:
16 June 2021 - 4:15am
Document Type:
Presentation Slides
Document Year:
2021
Event:
Presenters Name:
Xinghong Qin
Paper Code:
2181

Abstract 

Abstract: 

Nowadays a steganography has to face challenges to both feature-based staganalysis and convolutional neural network (CNN) based steganalysis. In this paper, we present a novel steganographic scheme to incorporate synchronizing modification directions and iterative adversarial perturbations to enhance steganographic performance. Firstly an existing steganographic function is employed to compute initial costs. Then the secret message bits are embedded following clustering modification directions profile. If the target CNN classifier discriminates the resulting stego image as the correct class, we change costs in adversarial manners, and then choose a sub-image to re-embed message with changed costs. Adversarial intensity will be iteratively increased until the adversarial stego image can deceive the target CNN classifier, which guarantees that applied adversarial perturbations are minimal and it is unnecessary to search the optimal adversarial intensity. Experiments demonstrate that the proposed method effectively enhances security to counter both feature-based classifiers and CNN classifiers, no matter they are targeted or non-targeted.

up
0 users have voted:

Dataset Files

ITE_SYN_Presentation-v1.05.pdf

(42)