Author name cluster

Chunyi Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

1 author row

AAAI Conference 2026 Conference Paper

Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content?

Naen Xu
Jinghuai Zhang
Changjiang Li
Hengyu An
Chunyi Zhou
Jun Wang
Boyu Xu
Yuyuan Li

Large vision-language models (LVLMs) have achieved remarkable advancements in multimodal reasoning tasks. However, their widespread accessibility raises critical concerns about potential copyright infringement. Will LVLMs accurately recognize and comply with copyright regulations when encountering copyrighted content (i.e., user input, retrieved documents) in the context? Failure to comply with copyright regulations may lead to serious legal and ethical consequences, particularly when LVLMs generate responses based on copyrighted materials (e.g., retrieved book experts, news reports). In this paper, we present a comprehensive evaluation of various LVLMs, examining how they handle copyrighted content – such as book excerpts, news articles, music lyrics, and code documentation when they are presented as visual inputs. To systematically measure copyright compliance, we introduce a large-scale benchmark dataset comprising 50,000 multimodal query-content pairs designed to evaluate how effectively LVLMs handle queries that could lead to copyright infringement. Given that real-world copyrighted content may or may not include a copyright notice, the dataset includes query-content pairs in two distinct scenarios: with and without a copyright notice. For the former, we extensively cover four types of copyright notices to account for different cases. Our evaluation reveals that even state-of-the-art closed-source LVLMs exhibit significant deficiencies in recognizing and respecting the copyrighted content, even when presented with the copyright notice. To solve this limitation, we introduce a novel tool-augmented defense framework for copyright compliance, which reduces infringement risks in all scenarios. Our findings underscore the importance of developing copyright-aware LVLMs to ensure the responsible and lawful use of copyrighted content.

PDF Details DOI

AAAI Conference 2026 Conference Paper

DP-GenG: Differentially Private Dataset Distillation Guided by DP-Generated Data

Shuo Shi
Jinghuai Zhang
Shijie Jiang
Chunyi Zhou
Yuyuan Li
Mengying Zhu
Yangyang Wu
Tianyu Du

Dataset distillation (DD) compresses large datasets into smaller ones while preserving the performance of models trained on them. Although DD is often assumed to enhance data privacy by aggregating over individual examples, recent studies reveal that standard DD can still leak sensitive information from the original dataset due to the lack of formal privacy guarantees. Existing differentially private (DP)-DD methods attempt to mitigate this risk by injecting noise into the distillation process. However, they often fail to fully leverage the original dataset, resulting in degraded realism and utility. This paper introduces DP-GENG, a novel framework that addresses the key limitations of current DP-DD by leveraging DP-generated data. Specifically, DP-GENG initializes the distilled dataset with DP-generated data to enhance realism. Then, generated data refines the DP-feature matching technique to distill the original dataset under a small privacy budget, and trains an expert model to align the distilled examples with their class distribution. Furthermore, we design a privacy budget allocation strategy to determine budget consumption across DP components and provide a theoretical analysis of the overall privacy guarantees. Extensive experiments show that DP-GENG significantly outperforms state-of-the-art DP-DD methods in terms of both dataset utility and robustness against membership inference attacks, establishing a new paradigm for privacy-preserving dataset distillation.

PDF Details DOI

EAAI Journal 2026 Journal Article

Intellectual property protection for deep learning model and dataset intelligence

Yongqi Jiang
Yansong Gao
Chunyi Zhou
Hongsheng Hu
Si Chen
Anmin Fu
Willy Susilo

With the growing applications of Deep Learning (DL), especially recent spectacular achievements of Large Language Models (LLMs) such as ChatGPT and LLaMA, the commercial significance of these remarkable models has soared. However, acquiring well-trained models is costly and resource-intensive. It requires a considerably high-quality dataset, substantial investment in dedicated architecture design, expensive computational resources, and efforts to develop technical expertise. Consequently, protecting the Intellectual Property (IP) of well-trained models is becoming a priority. Despite the importance of IP protection, most existing surveys focus narrowly on model level intelligence, with limited attention given to protecting the valuable dataset intelligence. This indicates a significant gap in existing surveys regarding comprehensive strategies for safeguarding the IP of datasets. In this survey, we address the gap by presenting a comprehensive overview of both model and dataset IP protection in DL context. Firstly, according to the requirements for effective IP protection design, this work systematically summarizes the general and scheme-specific performance evaluation metrics. Secondly, from proactive IP infringement prevention and reactive IP ownership verification perspectives, it comprehensively investigates and analyzes the existing IP protection methods for both dataset and model intelligence. Additionally, from the standpoint of training settings, it delves into the unique challenges that distributed learning poses to IP protection compared to centralized settings. Furthermore, this work examines various attacks faced by deep IP protection techniques. Finally, we outline prospects for promising future directions that may act as a guide for innovative research.

Details DOI

AAAI Conference 2025 Conference Paper

CAMH: Advancing Model Hijacking Attack in Machine Learning

Xing He
Jiahao Chen
Yuwen Pu
Qingming Li
Chunyi Zhou
Yingcai Wu
Jinbao Li
Shouling Ji

In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where adversaries manipulate models to perform unintended tasks, leading to significant security and ethical concerns, like turning an ordinary image classifier into a tool for detecting faces in pornographic content, all without the model owner’s knowledge. This paper introduces Category-Agnostic Model Hijacking (CAMH), a novel model hijacking attack method capable of addressing the challenges of class number mismatch, data distribution divergence, and performance balance between the original and hijacking tasks. CAMH incorporates synchronized training layers, random noise optimization, and a dual-loop optimization approach to ensure minimal impact on the original task’s performance while effectively executing the hijacking task. We evaluate CAMH across multiple benchmark datasets and network architectures, demonstrating its potent attack effectiveness while ensuring minimal degradation in the performance of the original task.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Enhancing Adversarial Transferability with Adversarial Weight Tuning

Jiahao Chen
Zhou Feng
Rui Zeng
Yuwen Pu
Chunyi Zhou
Yi Jiang
Yuyou Gan
Jinbao Li

Deep neural networks (DNNs) are vulnerable to adversarial examples (AEs) that mislead the model while appearing benign to human observers. A critical concern is the transferability of AEs, which enables black-box attacks without direct access to the target model. However, many previous attacks have failed to explain the intrinsic mechanism of adversarial transferability, lacking a unified and representative metric for transferability as well. In this paper, we rethink the property of transferable AEs and develop a novel metric to measure transferability from the perspective of generalization. Building on insights from this metric, we analyze the generalization of AEs across models with different architectures and prove that we can find a local perturbation to mitigate the gap between surrogate and target models. We further establish the inner connections between model smoothness and flat local maxima, both of which contribute to the transferability of AEs. Further, we propose a new adversarial attack algorithm, Adversarial Weight Tuning (AWT), which adaptively adjusts the parameters of the surrogate model using generated AEs to optimize the flat local maxima and model smoothness simultaneously, without the need for extra data. AWT is a data-free tuning method that combines gradient-based and model-related attack methods to enhance the transferability of AEs. Extensive experiments on a variety of models with different architectures on ImageNet demonstrate that AWT yields superior performance over other attacks, with an average increase of nearly 5% and 10% attack success rates on CNN-based and Transformer-based models, respectively, compared to state-of-the-art attacks.

PDF Details DOI