41 citations · 112 across the 26 of their papers we have counts for
28 papers
Decision Uncertainty-Oriented Watermarking (DUOW): Securing Multi-Agent Routing Against Policy Cloning
Ziming Zhang, Li Li, Guorui Feng +3
Routing policies in Multi-Agent Systems (MAS) represent valuable intellectual property, yet their exposure through execution logs creates significant risks of unauthorized policy c…
Trigger Where It Hurts: Unveiling Hidden Backdoors through Sensitivity with Sensitron
Gejian Zhao, Hanzhou Wu, Xinpeng Zhang
Backdoor attacks pose a significant security threat to natural language processing (NLP) systems, but existing methods lack explainable trigger mechanisms and fail to quantitativel…
ShadowCoT: Cognitive Hijacking for Stealthy Reasoning Backdoors in LLMs
Gejian Zhao, Hanzhou Wu, Xinpeng Zhang +1
Chain-of-Thought (CoT) enhances an LLM's ability to perform complex reasoning tasks, but it also introduces new security issues. In this work, we present ShadowCoT, a novel backdoo…
Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
Xiangyu Zhao, Hanzhou Wu, Xinpeng Zhang
Recent years have witnessed the prosperous development of Graph Self-supervised Learning (GSSL), which enables to pre-train transferable foundation graph encoders. However, the eas…
StegGuard: Fingerprinting Self-supervised Pre-trained Encoders via Secrets Embeder and Extractor
Xingdong Ren, Tianxing Zhang, Hanzhou Wu +3
In this work, we propose StegGuard, a novel fingerprinting mechanism to verify the ownership of the suspect pre-trained encoder using steganography. A critical perspective in StegG…
Generative Model Watermarking Suppressing High-Frequency Artifacts
Li Zhang, Yong Liu, Xinpeng Zhang +1
Protecting deep neural networks (DNNs) against intellectual property (IP) infringement has attracted an increasing attention in recent years. Recent advances focus on IP protection…
Robust and Lossless Fingerprinting of Deep Neural Networks via Pooled Membership Inference
Hanzhou Wu
Deep neural networks (DNNs) have already achieved great success in a lot of application areas and brought profound changes to our society. However, it also raises new security prob…
AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learning
Tianxing Zhang, Hanzhou Wu, Xiaofeng Lu +1
As a self-supervised learning paradigm, contrastive learning has been widely used to pre-train a powerful encoder as an effective feature extractor for various downstream tasks. Th…
Robust and Imperceptible Black-box DNN Watermarking Based on Fourier Perturbation Analysis and Frequency Sensitivity Clustering
Yong Liu, Hanzhou Wu, Xinpeng Zhang
Recently, more and more attention has been focused on the intellectual property protection of deep neural networks (DNNs), promoting DNN watermarking to become a hot research topic…
Verifying Integrity of Deep Ensemble Models by Lossless Black-box Watermarking with Sensitive Samples
Lina Lin, Hanzhou Wu
With the widespread use of deep neural networks (DNNs) in many areas, more and more studies focus on protecting DNN models from intellectual property (IP) infringement. Many existi…
Autoregressive Linguistic Steganography Based on BERT and Consistency Coding
Xiaoyan Zheng, Hanzhou Wu
Linguistic steganography (LS) conceals the presence of communication by embedding secret information into a text. How to generate a high-quality text carrying secret information is…
Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
Tianyu Yang, Hanzhou Wu, Biao Yi +2
Linguistic steganography (LS) aims to embed secret information into a highly encoded text for covert communication. It can be roughly divided to two main categories, i.e., modifica…
Generating Watermarked Adversarial Texts
Mingjie Li, Hanzhou Wu, Xinpeng Zhang
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…
Graph Representation Learning for Spatial Image Steganalysis
Qiyun Liu, Hanzhou Wu
In this paper, we introduce a graph representation learning architecture for spatial image steganalysis, which is motivated by the assumption that steganographic modifications unav…
Exploiting Language Model for Efficient Linguistic Steganalysis
Biao Yi, Hanzhou Wu, Guorui Feng +1
Recent advances in linguistic steganalysis have successively applied CNN, RNN, GNN and other efficient deep models for detecting secret information in generative texts. These metho…
Structural Watermarking to Deep Neural Networks via Network Channel Pruning
Xiangyu Zhao, Yinzhe Yao, Hanzhou Wu +1
In order to protect the intellectual property (IP) of deep neural networks (DNNs), many existing DNN watermarking techniques either embed watermarks directly into the DNN parameter…
Orientation Convolutional Networks for Image Recognition
Yalan Qin, Guorui Feng, Hanzhou Wu +2
Deep Convolutional Neural Networks (DCNNs) are capable of obtaining powerful image representations, which have attracted great attentions in image recognition. However, they are li…
Hiding Data Hiding
Hanzhou Wu, Gen Liu, Xinpeng Zhang
Data hiding is the art of hiding secret data into a cover object such as digital image for covert communication. In this paper, we make the first step towards hiding ``data hiding'…
Watermarking Graph Neural Networks by Random Graphs
Xiangyu Zhao, Hanzhou Wu, Xinpeng Zhang
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 deploye…
Game-theoretic Analysis to Content-adaptive Reversible Watermarking
Hanzhou Wu, Xinpeng Zhang
While many games were designed for steganography and robust watermarking, few focused on reversible watermarking. We present a two-encoder game related to the rate-distortion optim…
Steganographer Identification
Hanzhou Wu
Conventional steganalysis detects the presence of steganography within single objects. In the real-world, we may face a complex scenario that one or some of multiple users called a…
Feature Bagging for Steganographer Identification
Hanzhou Wu
Traditional steganalysis algorithms focus on detecting the existence of steganography in a single object. In practice, one may face a complex scenario where one or some of multiple…
Reversible Video Data Hiding Using Zero QDCT Coefficient-Pairs
Yi Chen, Hongxia Wang, Hanzhou Wu +1
H.264/Advanced Video Coding (AVC) is one of the most commonly used video compression standard currently. In this paper, we propose a Reversible Data Hiding (RDH) method based on H.…
The Cut and Dominating Set Problem in A Steganographer Network
Hanzhou Wu, Wei Wang, Jing Dong +2
A steganographer network corresponds to a graphic structure that the involved vertices (or called nodes) denote social entities such as the data encoders and data decoders, and the…