Skip to search formSkip to main contentSkip to account menu

DUP-Net: Denoiser and Upsampler Network for 3D Adversarial Point Clouds Defense

A Denoiser and UPsampler Network (DUP-Net) structure as defenses for 3D adversarial point cloud classification, where the two modules reconstruct surface smoothness by dropping or adding points.
View on IEEE (opens in a new tab)

Reversible Data Hiding in Color Image With Grayscale Invariance

The unchanged gray version is utilized efficiently in both the embedding processes and the extracting processes, and the reversibility and the property of grayscale invariance are both achieved.
View on IEEE (opens in a new tab)

LG-GAN: Label Guided Adversarial Network for Flexible Targeted Attack of Point Cloud Based Deep Networks

The proposed LG-GAN can support flexible targeted attack on the fly while guaranteeing good attack performance and higher efficiency simultaneously, and is the first generation based 3D point cloud attack method.
View on IEEE (opens in a new tab)

Robust adaptive steganography based on generalized dither modulation and expanded embedding domain

View via Publisher (opens in a new tab)

Defining Joint Distortion for JPEG Steganography

This paper inspects the embedding change from the spatial domain and proposes a principle of Block Boundary Continuity (BBC) for defining JPEG joint distortion, which aims to restrain blocking artifacts caused by inter-block adjacent modifications and thus effectively preserve the spatial continuity at block boundaries.
View on ACM (opens in a new tab)

Comments on “Steganography Using Reversible Texture Synthesis”

This work proposes an attacking method on this steganography, which can not only detect the stego-images but can also extract the hidden messages.
View on IEEE (opens in a new tab)

Distortion Design for Secure Adaptive 3-D Mesh Steganography

A novel technique for steganography on 3-D meshes so as to resist steganalysis, which relies on some effective steganalytic features such as variation of vertex normal and outperforms the current state of the art.
View on IEEE (opens in a new tab)

Adversarial Examples Detection Beyond Image Space

This work proposes a method beyond image space by a two-stream architecture, in which the image stream focuses on the pixel artifacts and the gradient stream copes with the confidence artifacts, which outperforms the existing methods under oblivious attacks and is verified effective to defend omniscient attacks.
View on IEEE (opens in a new tab)

Adversarial Examples Against Deep Neural Network based Steganalysis

A new strategy is proposed that constructs enhanced covers against neural networks with the technique of adversarial examples and makes a tradeoff between the two analysis systems to improve the comprehensive security.
View on ACM (opens in a new tab)

Derivative-Based Steganographic Distortion and its Non-additive Extensions for Audio

A novel distortion is presented for audio steganography, inspired by the phenomenon that the modification of audio samples with the low amplitude will be easily detected, and the proposed distortion outperforms the state-of-the-art methods defending strong steganalytic methods.
View on IEEE (opens in a new tab)
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)