18 citations · 61 across the 51 of their papers we have counts for
55 papers
BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
Laiqiao Qin, Tianqing Zhu, Longxiang Gao +1
Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or exte…
Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives
Xiaolong Liu, Junjian Li, Yuan Xiao +4
Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without extensive prompt engineerin…
Fundus Image-based Glaucoma Screening via Retinal Knowledge-Oriented Dynamic Multi-Level Feature Integration
Chi Liu, Yuzhuo Zhou, Sheng Shen +9
While deep learning has advanced automated glaucoma screening via color fundus photography, existing purely data-driven models often overfit to confounding imaging artifacts and st…
Osmosis Distillation: Model Hijacking with the Fewest Samples
Yuchen Shi, Huajie Chen, Heng Xu +6
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation has eme…
From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
Yizhe Xie, Congcong Zhu, Xinyue Zhang +5
Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccu…
Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
Huajie Chen, Tianqing Zhu, Hailin Yang +7
Watermarking has emerged as a key defense against the misuse of machine-generated images (MGIs). Yet the robustness of these protections remains underexplored. To reveal the limits…
Turning Black Box into White Box: Dataset Distillation Leaks
Huajie Chen, Tianqing Zhu, Yuchen Zhong +7
Dataset distillation compresses a large real dataset into a small synthetic one, enabling models trained on the synthetic data to achieve performance comparable to those trained on…
Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
Linlin Wang, Tianqing Zhu, Laiqiao Qin +2
With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated sing…
Forgetting Similar Samples: Can Machine Unlearning Do it Better?
Heng Xu, Tianqing Zhu, Dayong Ye +3
Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extens…
Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection
Chi Liu, Tianqing Zhu, Wanlei Zhou +1
As deep image forgery powered by AI generative models, such as GANs, continues to challenge today's digital world, detecting AI-generated forgeries has become a vital security topi…
When Harmless Words Harm: A New Threat to LLM Safety via Conceptual Triggers
Zhaoxin Zhang, Borui Chen, Yiming Hu +3
Recent research on large language model (LLM) jailbreaks has primarily focused on techniques that bypass safety mechanisms to elicit overtly harmful outputs. However, such efforts…
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
Wei Wan, Yuxuan Ning, Zhicong Huang +7
Federated Learning (FL) is a distributed paradigm aimed at protecting participant data privacy by exchanging model parameters to achieve high-quality model training. However, this…
Graph Unlearning: Efficient Node Removal in Graph Neural Networks
Faqian Guan, Tianqing Zhu, Zhoutian Wang +2
With increasing concerns about privacy attacks and potential sensitive information leakage, researchers have actively explored methods to efficiently remove sensitive training data…
Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation
Huiqiang Chen, Tianqing Zhu, Xin Yu +1
Machine unlearning aims to remove the influence of specific samples from a trained model. A key challenge in this process is over-unlearning, where the model's performance on the r…
Bias Amplification in RAG: Poisoning Knowledge Retrieval to Steer LLMs
Linlin Wang, Tianqing Zhu, Laiqiao Qin +2
In Large Language Models, Retrieval-Augmented Generation (RAG) systems can significantly enhance the performance of large language models by integrating external knowledge. However…
Chain-of-Lure: A Universal Jailbreak Attack Framework using Unconstrained Synthetic Narratives
Wenhan Chang, Tianqing Zhu, Yu Zhao +3
In the era of rapid generative AI development, interactions with large language models (LLMs) pose increasing risks of misuse. Prior research has primarily focused on attacks using…
Safe and Reliable Diffusion Models via Subspace Projection
Huiqiang Chen, Tianqing Zhu, Linlin Wang +3
Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these m…
Do Fairness Interventions Come at the Cost of Privacy: Evaluations for Binary Classifiers
Huan Tian, Guangsheng Zhang, Bo Liu +3
While in-processing fairness approaches show promise in mitigating biased predictions, their potential impact on privacy leakage remains under-explored. We aim to address this gap…
Data-Free Model-Related Attacks: Unleashing the Potential of Generative AI
Dayong Ye, Tianqing Zhu, Shang Wang +4
Generative AI technology has become increasingly integrated into our daily lives, offering powerful capabilities to enhance productivity. However, these same capabilities can be ex…
AFed: Algorithmic Fair Federated Learning
Huiqiang Chen, Tianqing Zhu, Wanlei Zhou +1
Federated Learning (FL) has gained significant attention as it facilitates collaborative machine learning among multiple clients without centralizing their data on a server. FL ens…
Large Language Model Federated Learning with Blockchain and Unlearning for Cross-Organizational Collaboration
Xuhan Zuo, Minghao Wang, Tianqing Zhu +2
Large language models (LLMs) have transformed the way computers understand and process human language, but using them effectively across different organizations remains still diffi…
Vertical Federated Unlearning via Backdoor Certification
Mengde Han, Tianqing Zhu, Lefeng Zhang +2
Vertical Federated Learning (VFL) offers a novel paradigm in machine learning, enabling distinct entities to train models cooperatively while maintaining data privacy. This method…
Defending Against Neural Network Model Inversion Attacks via Data Poisoning
Shuai Zhou, Dayong Ye, Tianqing Zhu +1
Model inversion attacks pose a significant privacy threat to machine learning models by reconstructing sensitive data from their outputs. While various defenses have been proposed…
Large Language Models Merging for Enhancing the Link Stealing Attack on Graph Neural Networks
Faqian Guan, Tianqing Zhu, Wenhan Chang +2
Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a…