Chenglin Miao

Defending Autonomous Driving Perception against Adversarial Object-Based Attacks via Motion Planning

Zihao Liu, Yan Zhang, Yi Zhu, Lu Su et autres

Autonomous vehicles (AVs) rely on perception systems to detect surrounding objects using sensors such as cameras, LiDAR (Light Detection and Ranging), and millimeter-wave (mmWave) radar. However, recent studies have shown that attackers can deceive these systems by strategically placing adversarial objects (e.g., …

us (code pays fourni par la source)

Towards Privacy-Preserving and Heterogeneity-aware Split Federated Learning via Probabilistic Masking

Xingchen Wang, Feijie Wu, Chenglin Miao, Tianchun Li et autres

Split Federated Learning (SFL) has emerged as an efficient alternative to traditional Federated Learning (FL) by reducing client-side computation through model partitioning. However, exchanging of intermediate activations and model updates introduces significant privacy risks, especially from data reconstruction attacks that recover original …

us (code pays fourni par la source)

Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning

Aobo Chen, Chenxu Zhao, Chenglin Miao, Mengdi Huai

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On the other hand, the growing need for the right to be …

Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning

Aobo Chen, Chenxu Zhao, Chenglin Miao, Mengdi Huai

Large language models (LLMs) possess strong semantic understanding, driving significant progress in data mining applications. This is further enhanced by large reasoning models (LRMs), which provide explicit multi-step reasoning traces. On the other hand, the growing need for the right to be …

us (code pays fourni par la source)

Rethinking Fake Speech Detection: A Generalized Framework Leveraging Spectrogram Magnitude

Zihao Liu, Aobo Chen, Yan Zhang, Wensheng Zhang et autres

Rethinking Unlearnable Examples in Machine Unlearning

Chenxu Zhao, Wei Qian, Chenglin Miao, Mengdi Huai

us (code pays fourni par la source)

Towards Unveiling Vulnerabilities of Large Reasoning Models in Machine Unlearning

Aobo Chen, Chenxu Zhao, Chenglin Miao, Mengdi Huai

us (code pays fourni par la source)

Towards Real-Time Defense against Object-Based LiDAR Attacks in Autonomous Driving

Yan Zhang, Zihao Liu, Yi Zhu, Chenglin Miao

LiDAR (Light Detection and Ranging)-based object detection is a cornerstone of autonomous vehicle perception systems. Modern LiDAR perception relies heavily on deep neural networks (DNNs), which enable accurate object detection by learning geometric features from 3D point clouds. However, recent studies have …

us (code pays fourni par la source)

Dual-Bubble Coordinated Acoustic Micromanipulator for Multidirectional Object Rotation *

Yuyang Li, Zhongqiang Zhang, Chenglin Miao, Xu Du et autres

Micromanipulation techniques struggle to achieve three-dimensional rotational control at the microscale without compromising biocompatibility or spatial flexibility. Conventional methods based on mechanical contact, optical forces, or confined microfluidics constrain dynamic reconfiguration and surgical accessibility. Here, we introduce a dual-bubble acoustic micromanipulator that …

cn (code pays fourni par la source)

Acoustic-Actuated Robotic End-Effector for Open-Environment Microfluidics Manipulation

Yuyang Li, Chenglin Miao, Xu Du, Qiang Huang et autres

Efficient manipulation of microscale fluids in open environments remains a significant challenge due to dominant viscous forces, risks of evaporation, and limited integration with robotic systems, all of which impede rapid mass transfer critical for applications such as diagnostics, drug discovery, and …

cn (code pays fourni par la source)

Ecological Resilience, Industrial Digitization and Green Technology Innovation: Synergistic Development and Driving Mechanism

Aoxiang Zhang, Chenglin Miao, Zhengyan Chen, Zhenghan Yang et autres

Synergistic development of eco-resilience, green technological innovation, and industrial digitization can help to increase resource efficiency, reduce environmental impacts, and facilitate industrial transformation, thereby contributing to the long-term sustainability of economic growth and social well-being. Using the super-efficient SBM model and the …

cn (code pays fourni par la source)

An Online Defense against Object-based LiDAR Attacks in Autonomous Driving

Yan Zhang, Zihao Liu, Chongliu Jia, Yi Zhu et autres

LiDAR (Light Detection and Ranging) has been widely used in autonomous driving to perceive the surrounding environment of self-driving cars. Advanced LiDAR perception systems typically leverage deep neural networks (DNNs) to achieve high performance. However, the vulnerability of DNNs to malicious attacks …

us (code pays fourni par la source)