Search Results for author:
Found 51 papers, 9 papers with code
Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Models
Comprehensive experiments reveal that (1) Our method can effectively attribute fake images to their source models, achieving comparable attribution performance with the state-of-the-art method; (2) Our method has high scalability ability, which is well adapted to real-world attribution scenarios.
Purified and Unified Steganographic Network
It is also shown to be capable of imperceptibly carrying the steganographic networks in a purified network.
Object-oriented backdoor attack against image captioning
After training with the poisoned data, the attacked model behaves normally on benign images, but for poisoned images, the model will generate some sentences irrelevant to the given image.
PROMPT-IML: Image Manipulation Localization with Pre-trained Foundation Models Through Prompt Tuning
We observe that humans tend to discern the authenticity of an image based on both semantic and high-frequency information, inspired by which, the proposed framework leverages rich semantic knowledge from pre-trained visual foundation models to assist IML.
From Covert Hiding to Visual Editing: Robust Generative Video Steganography
Traditional video steganography methods are based on modifying the covert space for embedding, whereas we propose an innovative approach that embeds secret message within semantic feature for steganography during the video editing process.
Model Copyright Protection in Buyer-seller Environment
The main idea of ISNN is to make a DNN sensitive to the key and copyright information.
Steal My Artworks for Fine-tuning? A Watermarking Framework for Detecting Art Theft Mimicry in Text-to-Image Models
In various fine-tune scenarios and against watermark attack methods, our research confirms that analyzing the distribution of watermarks in artificially generated images reliably detects unauthorized mimicry.
PatchCraft: Exploring Texture Patch for Efficient AI-generated Image Detection
We observe that the texture patches of images tend to reveal more traces left by generative models compared to the global semantic information of the images.
Securing Fixed Neural Network Steganography
To deal with this issue, we propose a key-based FNNS scheme to improve the security of the FNNS, where we generate key-controlled perturbations from the FNN for data embedding.
Salient Object Detection in Optical Remote Sensing Images Driven by Transformer
KTM models the contextual correlation knowledge of two middle-level features of different scales based on the self-attention mechanism, and transfers the knowledge to the raw features to generate more discriminative features.
Physical Invisible Backdoor Based on Camera Imaging
Subsequently, we elaborate a special network architecture, which is easily compromised by our backdoor attack, by leveraging the attributes of the CFA interpolation algorithm and combining it with the feature extraction block in the camera identification model.
DRAW: Defending Camera-shooted RAW against Image Manipulation
RAW files are the initial measurement of scene radiance widely used in most cameras, and the ubiquitously-used RGB images are converted from RAW data through Image Signal Processing (ISP) pipelines.
RetouchingFFHQ: A Large-scale Dataset for Fine-grained Face Retouching Detection
However, the lack of large-scale and fine-grained face retouching datasets has been a major obstacle to progress in this field.
Towards Deep Network Steganography: From Networks to Networks
In this paper, we propose deep network steganography for the covert communication of DNN models.
StyleStegan: Leak-free Style Transfer Based on Feature Steganography
Our method consists of two main components: a style transfer method that accomplishes artistic stylization on the original image and an image steganography method that embeds content feature secrets on the stylized image.
Decision-based iterative fragile watermarking for model integrity verification
Our method has some advantages: (1) the iterative update of samples is done in a decision-based black-box manner, relying solely on the predicted probability distribution of the target model, which reduces the risk of exposure to adversarial attacks, (2) the small-amplitude multiple iterations approach allows the fragile samples to perform well visually, with a PSNR of 55 dB in TinyImageNet compared to the original samples, (3) even with changes in the overall parameters of the model of magnitude 1e-4, the fragile samples can detect such changes, and (4) the method is independent of the specific model structure and dataset.
Generative Steganographic Flow
In the forward mapping, secret data is hidden in the input latent of Glow model to generate stego images.
Generative Steganography Diffusion
However, existing GAN-based GS methods cannot completely recover the hidden secret data due to the lack of network invertibility, while Flow-based methods produce poor image quality due to the stringent reversibility restriction in each module.
Multi-modal Fake News Detection on Social Media via Multi-grained Information Fusion
The easy sharing of multimedia content on social media has caused a rapid dissemination of fake news, which threatens society's stability and security.
Steganography of Steganographic Networks
We propose to disguise a steganographic network (termed as the secret DNN model) into a stego DNN model which performs an ordinary machine learning task (termed as the stego task).
Lightweight Salient Object Detection in Optical Remote-Sensing Images via Semantic Matching and Edge Alignment
Then, semantic kernels are used to activate salient object locations in two groups of high-level features through dynamic convolution operations in DSMM.
Exploring Depth Information for Face Manipulation Detection
As one of the important face features, the face depth map, which has shown to be effective in other areas such as the face recognition or face detection, is unfortunately paid little attention to in literature for detecting the manipulated face images.
Learning to Immunize Images for Tamper Localization and Self-Recovery
Image immunization (Imuge) is a technology of protecting the images by introducing trivial perturbation, so that the protected images are immune to the viruses in that the tampered contents can be auto-recovered.
RGB-T Semantic Segmentation with Location, Activation, and Sharpening
The highlight of LASNet is that we fully consider the characteristics of cross-modal features at different levels, and accordingly propose three specific modules for better segmentation.
Ranked #26 on
Thermal Image Segmentation
on MFN Dataset
Hiding Images in Deep Probabilistic Models
As an instantiation, we adopt a SinGAN, a pyramid of generative adversarial networks (GANs), to learn the patch distribution of one cover image.
Generative Model Watermarking Based on Human Visual System
Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing.
Neural network fragile watermarking with no model performance degradation
In the process of watermarking, we train a generative model with the specific loss function and secret key to generate triggers that are sensitive to the fine-tuning of the target classifier.
Generative Steganography Network
A new steganographic approach called generative steganography (GS) has emerged recently, in which stego images (images containing secret data) are generated from secret data directly without cover media.
Image Generation Network for Covert Transmission in Online Social Network
Online social networks have stimulated communications over the Internet more than ever, making it possible for secret message transmission over such noisy channels.
Robust Watermarking for Video Forgery Detection with Improved Imperceptibility and Robustness
We jointly train a 3D-UNet-based watermark embedding network and a decoder that predicts the tampering mask.
PCPT and ACPT: Copyright Protection and Traceability Scheme for DNN Models
Because the existing traceability mechanisms are used for models without watermarks, a small number of false-positives are generated.
Image Protection for Robust Cropping Localization and Recovery
Existing image cropping detection schemes ignore that recovering the cropped-out contents can unveil the purpose of the behaved cropping attack.
A DTCWT-SVD Based Video Watermarking resistant to frame rate conversion
To address this issue, we present a new video watermarking based on joint Dual-Tree Cosine Wavelet Transformation (DTCWT) and Singular Value Decomposition (SVD), which is resistant to frame rate conversion.
Multimodal Fake News Detection via CLIP-Guided Learning
The results indicate that the proposed framework has a better capability in mining crucial features for fake news detection.
Deniable Steganography
With a stego media discovered, the adversary could find out the sender or receiver and coerce them to disclose the secret message, which we name as coercive attack in this paper.
Imperceptible Backdoor Attack: From Input Space to Feature Representation
A U-net-based network is employed to generate concrete parameters of multinomial distribution for each benign input.
Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
In this paper, we propose a novel LS method to modify a given text by pivoting it between two different languages and embed secret data by applying a GLS-like information encoding strategy.
Invertible Image Dataset Protection
We develop a reversible adversarial example generator (RAEG) that introduces slight changes to the images to fool traditional classification models.
From Image to Imuge: Immunized Image Generation
At the recipient's side, the verifying network localizes the malicious modifications, and the original content can be approximately recovered by the decoder, despite the presence of the attacks.
Generating Watermarked Adversarial Texts
Adversarial example generation has been a hot spot in recent years because it can cause deep neural networks (DNNs) to misclassify the generated adversarial examples, which reveals the vulnerability of DNNs, motivating us to find good solutions to improve the robustness of DNN models.
On Generating Identifiable Virtual Faces
Our virtual face images are visually different from the original ones for privacy protection.
RWN: Robust Watermarking Network for Image Cropping Localization
At the recipient's side, ACP extracts the watermark from the attacked image, and we conduct feature matching on the original and extracted watermark to locate the position of the crop in the original image plane.
Hiding Images into Images with Real-world Robustness
The existing image embedding networks are basically vulnerable to malicious attacks such as JPEG compression and noise adding, not applicable for real-world copyright protection tasks.
Exploiting Language Model for Efficient Linguistic Steganalysis
Such kind of difference can be naturally captured by the language model used for generating stego texts.
Orientation Convolutional Networks for Image Recognition
With the propogation of the low-rank structure, the corresponding sparsity for representation of original Gabor filter bank can be significantly promoted.
Perceptual Robust Hashing for Color Images with Canonical Correlation Analysis
Local color features of significant corner points on outer boundaries of ring-ribbons are extracted through color vector angles (CVA), and color low-order moments (CLMs) is utilized to extract global color features.
Watermarking Graph Neural Networks by Random Graphs
Many learning tasks require us to deal with graph data which contains rich relational information among elements, leading increasing graph neural network (GNN) models to be deployed in industrial products for improving the quality of service.
Statistical Analysis of Signal-Dependent Noise: Application in Blind Localization of Image Splicing Forgery
Through statistical analysis of the SDN model, we assume that noise can be modeled as a Gaussian approximation for a certain brightness and propose a likelihood model for a noise level function.
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as four datasets MNIST, CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates for the adversary, functionality for the normal users, and invisibility scores for the administrators.
End-to-End Model for Speech Enhancement by Consistent Spectrogram Masking
The experiments comparing ourCSM based end-to-end model with other methods are conductedto confirm that the CSM accelerate the model training andhave significant improvements in speech quality.
Robust Degraded Face Recognition Using Enhanced Local Frequency Descriptor and Multi-scale Competition
Recognizing degraded faces from low resolution and blurred images are common yet challenging task.
