Tianqing Zhu

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…

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…

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…

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…

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…

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…

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…

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…

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…

Evaluating of Machine Unlearning: Robustness Verification Without Prior Modifications

Heng Xu, Tianqing Zhu, Wanlei Zhou

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. While extensive…

When Machine Unlearning Meets Retrieval-Augmented Generation (RAG): Keep Secret or Forget Knowledge?

Shang Wang, Tianqing Zhu, Dayong Ye +1

The deployment of large language models (LLMs) like ChatGPT and Gemini has shown their powerful natural language generation capabilities. However, these models can inadvertently le…

cs.CR2024★ 7 cited

The Emerged Security and Privacy of LLM Agent: A Survey with Case Studies

Feng He, Tianqing Zhu, Dayong Ye +3

Inspired by the rapid development of Large Language Models (LLMs), LLM agents have evolved to perform complex tasks. LLM agents are now extensively applied across various domains,…

QUEEN: Query Unlearning against Model Extraction

Huajie Chen, Tianqing Zhu, Lefeng Zhang +4

Model extraction attacks currently pose a non-negligible threat to the security and privacy of deep learning models. By querying the model with a small dataset and usingthe query r…

Update Selective Parameters: Federated Machine Unlearning Based on Model Explanation

Heng Xu, Tianqing Zhu, Lefeng Zhang +2

Federated learning is a promising privacy-preserving paradigm for distributed machine learning. In this context, there is sometimes a need for a specialized process called machine…

Really Unlearned? Verifying Machine Unlearning via Influential Sample Pairs

Heng Xu, Tianqing Zhu, Lefeng Zhang +1

Machine unlearning enables pre-trained models to eliminate the effects of partial training samples. Previous research has mainly focused on proposing efficient unlearning strategie…

Don't Forget Too Much: Towards Machine Unlearning on Feature Level

Heng Xu, Tianqing Zhu, Wanlei Zhou +1

Machine unlearning enables pre-trained models to remove the effect of certain portions of training data. Previous machine unlearning schemes have mainly focused on unlearning a clu…

cs.CR2024★ 5 cited

Federated TrustChain: Blockchain-Enhanced LLM Training and Unlearning

Xuhan Zuo, Minghao Wang, Tianqing Zhu +4

The development of Large Language Models (LLMs) faces a significant challenge: the exhausting of publicly available fresh data. This is because training a LLM needs a large demandi…