8 citations · 27 across the 20 of their papers we have counts for
20 papers
Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications
Yutao Shi, Xiaohan Zhang, Xiangjing Zhang +5
The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools. In this ecosystem, LLMs rely on natural langu…
Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations
Yuanmin Huang, Mi Zhang, Chen Chen +4
While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks. In this work, we for the fir…
A First Measurement Study on Authentication Security in Real-World Remote MCP Servers
Huijun Zhou, Xiaohan Zhang, Haozhe Zhang +3
The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly impo…
From Anchors to Supervision: Memory-Graph Guided Corpus-Free Unlearning for Large Language Models
Wenxuan Li, Zhenfei Zhang, Mi Zhang +4
Large language models (LLMs) may memorize sensitive or copyrighted content, raising significant privacy and legal concerns. While machine unlearning has emerged as a potential reme…
SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers
Xiang Yang, Feifei Li, Mi Zhang +3
Recent Text-to-Image (T2I) models based on rectified-flow transformers (e.g., SD3, FLUX) achieve high generative fidelity but remain vulnerable to unsafe semantics, especially when…
Unveiling the Resilience of LLM-Enhanced Search Engines against Black-Hat SEO Manipulation
Pei Chen, Geng Hong, Xinyi Wu +6
The emergence of Large Language Model-enhanced Search Engines (LLMSEs) has revolutionized information retrieval by integrating web-scale search capabilities with AI-powered summari…
3D-ANC: Adaptive Neural Collapse for Robust 3D Point Cloud Recognition
Yuanmin Huang, Wenxuan Li, Mi Zhang +3
Deep neural networks have recently achieved notable progress in 3D point cloud recognition, yet their vulnerability to adversarial perturbations poses critical security challenges…
Revisiting Backdoor Attacks on Time Series Classification in the Frequency Domain
Yuanmin Huang, Mi Zhang, Zhaoxiang Wang +2
Time series classification (TSC) is a cornerstone of modern web applications, powering tasks such as financial data analysis, network traffic monitoring, and user behavior analysis…
Safe Text-to-Image Generation: Simply Sanitize the Prompt Embedding
Huming Qiu, Guanxu Chen, Mi Zhang +3
In recent years, text-to-image (T2I) generation models have made significant progress in generating high-quality images that align with text descriptions. However, these models als…
No-Skim: Towards Efficiency Robustness Evaluation on Skimming-based Language Models
Shengyao Zhang, Mi Zhang, Xudong Pan +1
To reduce the computation cost and the energy consumption in large language models (LLM), skimming-based acceleration dynamically drops unimportant tokens of the input sequence pro…
JADE: A Linguistics-based Safety Evaluation Platform for Large Language Models
Mi Zhang, Xudong Pan, Min Yang
In this paper, we present JADE, a targeted linguistic fuzzing platform which strengthens the linguistic complexity of seed questions to simultaneously and consistently break a wide…
BELT: Old-School Backdoor Attacks can Evade the State-of-the-Art Defense with Backdoor Exclusivity Lifting
Huming Qiu, Junjie Sun, Mi Zhang +2
Deep neural networks (DNNs) are susceptible to backdoor attacks, where malicious functionality is embedded to allow attackers to trigger incorrect classifications. Old-school backd…
Neural Dehydration: Effective Erasure of Black-box Watermarks from DNNs with Limited Data
Yifan Lu, Wenxuan Li, Mi Zhang +2
To protect the intellectual property of well-trained deep neural networks (DNNs), black-box watermarks, which are embedded into the prediction behavior of DNN models on a set of sp…
Rethinking White-Box Watermarks on Deep Learning Models under Neural Structural Obfuscation
Yifan Yan, Xudong Pan, Mi Zhang +1
Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique f…
Exorcising ''Wraith'': Protecting LiDAR-based Object Detector in Automated Driving System from Appearing Attacks
Qifan Xiao, Xudong Pan, Yifan Lu +3
Automated driving systems rely on 3D object detectors to recognize possible obstacles from LiDAR point clouds. However, recent works show the adversary can forge non-existent cars…
A Certifiable Security Patch for Object Tracking in Self-Driving Systems via Historical Deviation Modeling
Xudong Pan, Qifan Xiao, Mi Zhang +1
Self-driving cars (SDC) commonly implement the perception pipeline to detect the surrounding obstacles and track their moving trajectories, which lays the ground for the subsequent…
Matryoshka: Stealing Functionality of Private ML Data by Hiding Models in Model
Xudong Pan, Yifan Yan, Shengyao Zhang +2
In this paper, we present a novel insider attack called Matryoshka, which employs an irrelevant scheduled-to-publish DNN model as a carrier model for covert transmission of multipl…
Cracking White-box DNN Watermarks via Invariant Neuron Transforms
Yifan Yan, Xudong Pan, Yining Wang +2
Recently, how to protect the Intellectual Property (IP) of deep neural networks (DNN) becomes a major concern for the AI industry. To combat potential model piracy, recent works ex…
MetaV: A Meta-Verifier Approach to Task-Agnostic Model Fingerprinting
Xudong Pan, Yifan Yan, Mi Zhang +1
For model piracy forensics, previous model fingerprinting schemes are commonly based on adversarial examples constructed for the owner's model as the \textit{fingerprint}, and veri…
Exploring the Security Boundary of Data Reconstruction via Neuron Exclusivity Analysis
Xudong Pan, Mi Zhang, Yifan Yan +2
Among existing privacy attacks on the gradient of neural networks, \emph{data reconstruction attack}, which reverse engineers the training batch from the gradient, poses a severe t…