Hongwei Li

Towards Scalable Fuzzy PSI via Efficient Fuzzy Matching

Meng Hao, Xinpeng Yang, Hanxiao Chen +5

In this paper, we present scalable fuzzy PSI protocols for general $L_{p \in [1, \infty]}$ distance, supporting both low- and high-dimensional sets. The core technique is two effic…

Trigger the Straggler: Load Hijack on Mixture-of-Experts LLMs

Rui Zhang, Wenbo Jiang, Hongwei Li +4

Expert parallelism (EP) is a common strategy for serving large Mixture-of-Experts (MoE) models across multiple GPUs by distributing experts among devices. Router decisions then det…

EvoTrustRAG: Evolution-Aware Conflict Attribution and Evidence Handling for Reliable Retrieval-Augmented Generation

Xi Nie, Hongwei Li, Shenghao Wu +3

Retrieval-Augmented Generation (RAG) improves the factuality of large language models with external knowledge, yet conflicting evidence remains a fundamental challenge in dynamic a…

InkShield: Writing Style Protection Against Unauthorized Handwriting Mimicry

Jian Xiong, Wenbo Jiang, Zihan Wang +4

Recent handwritten text generators can reproduce a writer's style from publicly available references, posing risks of document forgery and identity misuse. An attacker may use a pu…

When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines

Xi Nie, Hongwei Li, Shenghao Wu +3

Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection. Existing stu…

Black-Box Skill Stealing Attack from Proprietary LLM Agents: An Empirical Study

Zihan Wang, Rui Zhang, Yu Liu +4

Large language model (LLM) agents increasingly rely on skills to package reusable capabilities through instructions, tools, and resources. High-quality skills embed expert knowledg…

The Art of (Mis)alignment: How Fine-Tuning Methods Effectively Misalign and Realign LLMs in Post-Training

Rui Zhang, Hongwei Li, Yun Shen +6

The deployment of large language models (LLMs) raises significant ethical and safety concerns. While LLM alignment techniques are adopted to improve model safety and trustworthines…

BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language Models

Zihan Wang, Hongwei Li, Rui Zhang +2

Chat template is a common technique used in the training and inference stages of Large Language Models (LLMs). It can transform input and output data into role-based and templated…

State Backdoor: Towards Stealthy Real-world Poisoning Attack on Vision-Language-Action Model in State Space

Ji Guo, Wenbo Jiang, Yansong Lin +6

Vision-Language-Action (VLA) models are widely deployed in safety-critical embodied AI applications such as robotics. However, their complex multimodal interactions also expose new…

Hidden Tail: Adversarial Image Causing Stealthy Resource Consumption in Vision-Language Models

Rui Zhang, Zihan Wang, Tianli Yang +5

Vision-Language Models (VLMs) are increasingly deployed in real-world applications, but their high inference cost makes them vulnerable to resource consumption attacks. Prior attac…

ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models

Zihan Wang, Rui Zhang, Hongwei Li +4

Backdoor attacks pose a significant threat to Large Language Models (LLMs), where adversaries can embed hidden triggers to manipulate LLM's outputs. Most existing defense methods,…

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks

Rui Zhang, Yun Shen, Hongwei Li +5

Recent research highlights concerns about the trustworthiness of third-party Pre-Trained Language Models (PTLMs) due to potential backdoor attacks. These backdoored PTLMs, however,…

BadLingual: A Novel Lingual-Backdoor Attack against Large Language Models

Zihan Wang, Hongwei Li, Rui Zhang +5

In this paper, we present a new form of backdoor attack against Large Language Models (LLMs): lingual-backdoor attacks. The key novelty of lingual-backdoor attacks is that the lang…

cs.CR2025★ 1 cited

MPMA: Preference Manipulation Attack Against Model Context Protocol

Zihan Wang, Rui Zhang, Yu Liu +5

Model Context Protocol (MCP) standardizes interface mapping for large language models (LLMs) to access external data and tools, which revolutionizes the paradigm of tool selection…

TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model

Ji Guo, Peihong Chen, Wenbo Jiang +6

Multimodal diffusion models for image editing generate outputs conditioned on both textual instructions and visual inputs, aiming to modify target regions while preserving the rest…

Combinational Backdoor Attack against Customized Text-to-Image Models

Wenbo Jiang, Jiaming He, Hongwei Li +6

Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as…

OnePath: Efficient and Privacy-Preserving Decision Tree Inference in the Cloud

Shuai Yuan, Hongwei Li, Xinyuan Qian +1

The vast storage capacity and computational power of cloud servers have led to the widespread outsourcing of machine learning inference services. While offering significant operati…

cs.CR2024★ 1 cited

BAZAM: A Blockchain-Assisted Zero-Trust Authentication in Multi-UAV Wireless Networks

Mingyue Xie, Zheng Chang, Osama Alfarraj +3

Unmanned aerial vehicles (UAVs) are vulnerable to interception and attacks when operated remotely without a unified and efficient identity authentication. Meanwhile, the openness o…