Search Results for author: Yi Shi

Found 38 papers, 4 papers with code

CS3: Cascade SAM for Sperm Segmentation

1 code implementation4 Jul 2024 Yi Shi, Xu-Peng Tian, Yun-Kai Wang, Tie-Yi Zhang, Bin Yao, Hui Wang, Yong Shao, Cen-Cen Wang, Rong Zeng, De-Chuan Zhan

Automated sperm morphology analysis plays a crucial role in the assessment of male fertility, yet its efficacy is often compromised by the challenges in accurately segmenting sperm images.

Boosting Large-scale Parallel Training Efficiency with C4: A Communication-Driven Approach

no code implementations7 Jun 2024 Jianbo Dong, Bin Luo, Jun Zhang, Pengcheng Zhang, Fei Feng, Yikai Zhu, Ang Liu, Zian Chen, Yi Shi, Hairong Jiao, Gang Lu, Yu Guan, Ennan Zhai, Wencong Xiao, Hanyu Zhao, Man Yuan, Siran Yang, Xiang Li, Jiamang Wang, Rui Men, Jianwei Zhang, Huang Zhong, Dennis Cai, Yuan Xie, Binzhang Fu

By leveraging this feature, C4 can rapidly identify the faulty components, swiftly isolate the anomaly, and restart the task, thereby avoiding resource wastage caused by delays in anomaly detection.

Anomaly Detection

SpotNet: An Image Centric, Lidar Anchored Approach To Long Range Perception

no code implementations24 May 2024 Louis Foucard, Samar Khanna, Yi Shi, Chi-Kuei Liu, Quinn Z Shen, Thuyen Ngo, Zi-Xiang Xia

In this paper, we propose SpotNet: a fast, single stage, image-centric but LiDAR anchored approach for long range 3D object detection.

3D Object Detection object-detection +1

Securing NextG Systems against Poisoning Attacks on Federated Learning: A Game-Theoretic Solution

no code implementations28 Dec 2023 Yalin E. Sagduyu, Tugba Erpek, Yi Shi

This paper studies the poisoning attack and defense interactions in a federated learning (FL) system, specifically in the context of wireless signal classification using deep learning for next-generation (NextG) communications.

Federated Learning

Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstruction

no code implementations10 Nov 2023 Shanghao Shi, Ning Wang, Yang Xiao, Chaoyu Zhang, Yi Shi, Y. Thomas Hou, Wenjing Lou

Unlike existing approaches treating models as black boxes, Scale-MIA recognizes the importance of the intricate architecture and inner workings of machine learning models.

Federated Learning

Controllable Motion Diffusion Model

no code implementations1 Jun 2023 Yi Shi, Jingbo Wang, Xuekun Jiang, Bo Dai

To enable real-time motion synthesis with diffusion models in response to time-varying control signals, we propose the framework of the Controllable Motion Diffusion Model (COMODO).

Image Generation Motion Synthesis

Jamming Attacks on Decentralized Federated Learning in General Multi-Hop Wireless Networks

no code implementations12 Jan 2023 Yi Shi, Yalin E. Sagduyu, Tugba Erpek

We show that the DFL performance can be significantly reduced by jamming attacks launched in a wireless network and characterize the attack surface as a vulnerability study before the safe deployment of DFL over wireless networks.

Federated Learning

Sensing-Throughput Tradeoffs with Generative Adversarial Networks for NextG Spectrum Sharing

no code implementations27 Dec 2022 Yi Shi, Yalin E. Sagduyu

In this paper, we present a generative adversarial network (GAN) approach to generate synthetic sensing results to augment the training data for the deep learning classifier so that the sensing time can be reduced (and thus the transmission time can be increased) while keeping high accuracy of the classifier.

Generative Adversarial Network

Rethinking the Detection Head Configuration for Traffic Object Detection

no code implementations8 Oct 2022 Yi Shi, Jiang Wu, Shixuan Zhao, Gangyao Gao, Tao Deng, Hongmei Yan

The first is the detection head and object distribution matching strategy, which guides the rational configuration of detection head, so as to leverage multi-scale features to effectively detect objects at vastly different scales.

Object object-detection +2

Identifying Ambiguous Similarity Conditions via Semantic Matching

1 code implementation CVPR 2022 Han-Jia Ye, Yi Shi, De-Chuan Zhan

To this end, we introduce a novel evaluation criterion by predicting the comparison's correctness after assigning the learned embeddings to their optimal conditions, which measures how much WS-CSL could cover latent semantics as the supervised model.

Federated Learning for Distributed Spectrum Sensing in NextG Communication Networks

no code implementations6 Apr 2022 Yi Shi, Yalin E. Sagduyu, Tugba Erpek

In this paper, distributed federated learning over a multi-hop wireless network is considered to collectively train a DNN for signal identification.

Anomaly Detection Federated Learning

Jamming Attacks on Federated Learning in Wireless Networks

no code implementations13 Jan 2022 Yi Shi, Yalin E. Sagduyu

Federated learning (FL) offers a decentralized learning environment so that a group of clients can collaborate to train a global model at the server, while keeping their training data confidential.

Federated Learning

C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

no code implementations26 Oct 2021 Di wu, Yi Shi, Ziyu Wang, Jie Yang, Mohamad Sawan

Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction.

Compressive Sensing Seizure prediction

A novel framework to quantify uncertainty in peptide-tandem mass spectrum matches with application to nanobody peptide identification

no code implementations15 Oct 2021 Chris McKennan, Zhe Sang, Yi Shi

To address these issues, we then develop a novel framework and method that treats peptide-spectrum matching as a Bayesian model selection problem with an incomplete model space, which are, to our knowledge, the first to account for all sources of PSM error without relying on the aforementioned assumptions.

Model Selection

Adversarial Attacks against Deep Learning Based Power Control in Wireless Communications

no code implementations16 Sep 2021 Brian Kim, Yi Shi, Yalin E. Sagduyu, Tugba Erpek, Sennur Ulukus

The DNN that corresponds to a regression model is trained with channel gains as the input and returns transmit powers as the output.

Membership Inference Attack and Defense for Wireless Signal Classifiers with Deep Learning

no code implementations22 Jul 2021 Yi Shi, Yalin E. Sagduyu

An over-the-air membership inference attack (MIA) is presented to leak private information from a wireless signal classifier.

Inference Attack Membership Inference Attack

Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN

no code implementations26 Mar 2021 Congyi Wang, Yu Chen, Bin Wang, Yi Shi

GAN-based neural vocoders, such as Parallel WaveGAN and MelGAN have attracted great interest due to their lightweight and parallel structures, enabling them to generate high fidelity waveform in a real-time manner.

Polyphone Disambiguition in Mandarin Chinese with Semi-Supervised Learning

no code implementations1 Feb 2021 Yi Shi, Congyi Wang, Yu Chen, Bin Wang

In this paper, we propose a novel semi-supervised learning (SSL) framework for Mandarin Chinese polyphone disambiguation that can potentially leverage unlimited unlabeled text data.

Polyphone disambiguation

Adversarial Machine Learning for Flooding Attacks on 5G Radio Access Network Slicing

no code implementations21 Jan 2021 Yi Shi, Yalin E. Sagduyu

We show that the portion of the reward achieved by real requests may be much less than the reward that would be achieved when there was no attack.

BIG-bench Machine Learning Reinforcement Learning (RL)

How to Attack and Defend NextG Radio Access Network Slicing with Reinforcement Learning

no code implementations14 Jan 2021 Yi Shi, Yalin E. Sagduyu, Tugba Erpek, M. Cenk Gursoy

In this paper, reinforcement learning (RL) for network slicing is considered in NextG radio access networks, where the base station (gNodeB) allocates resource blocks (RBs) to the requests of user equipments and aims to maximize the total reward of accepted requests over time.

Networking and Internet Architecture

Adversarial Machine Learning for 5G Communications Security

no code implementations7 Jan 2021 Yalin E. Sagduyu, Tugba Erpek, Yi Shi

For the second attack, the adversary spoofs wireless signals with the generative adversarial network (GAN) to infiltrate the physical layer authentication mechanism based on a deep learning classifier that is deployed at the 5G base station.

BIG-bench Machine Learning Generative Adversarial Network

Reinforcement Learning for Dynamic Resource Optimization in 5G Radio Access Network Slicing

no code implementations14 Sep 2020 Yi Shi, Yalin E. Sagduyu, Tugba Erpek

The paper presents a reinforcement learning solution to dynamic resource allocation for 5G radio access network slicing.

Q-Learning reinforcement-learning +1

Multi-View Fusion of Sensor Data for Improved Perception and Prediction in Autonomous Driving

no code implementations27 Aug 2020 Sudeep Fadadu, Shreyash Pandey, Darshan Hegde, Yi Shi, Fang-Chieh Chou, Nemanja Djuric, Carlos Vallespi-Gonzalez

Our model builds on a state-of-the-art Bird's-Eye View (BEV) network that fuses voxelized features from a sequence of historical LiDAR data as well as rasterized high-definition map to perform detection and prediction tasks.

Autonomous Driving object-detection +2

Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers

no code implementations25 Jun 2020 Yi Shi, Kemal Davaslioglu, Yalin E. Sagduyu

As machine learning (ML) algorithms are used to process wireless signals to make decisions such as PHY-layer authentication, the training data characteristics (e. g., device-level information) and the environment conditions (e. g., channel information) under which the data is collected may leak to the ML model.

Inference Attack Membership Inference Attack

Unsupervised Learning of Global Registration of Temporal Sequence of Point Clouds

no code implementations17 Jun 2020 Lingjing Wang, Yi Shi, Xiang Li, Yi Fang

Global registration of point clouds aims to find an optimal alignment of a sequence of 2D or 3D point sets.

Unsupervised Deep Shape Descriptor With Point Distribution Learning

1 code implementation CVPR 2020 Yi Shi, Mengchen Xu, Shuaihang Yuan, Yi Fang

This paper proposes a novel probabilistic framework for the learning of unsupervised deep shape descriptors with point distribution learning.

3D Shape Classification 3D Shape Retrieval +2

Deep Learning for Wireless Communications

no code implementations12 May 2020 Tugba Erpek, Timothy J. O'Shea, Yalin E. Sagduyu, Yi Shi, T. Charles Clancy

Existing communication systems exhibit inherent limitations in translating theory to practice when handling the complexity of optimization for emerging wireless applications with high degrees of freedom.

When Wireless Security Meets Machine Learning: Motivation, Challenges, and Research Directions

no code implementations24 Jan 2020 Yalin E. Sagduyu, Yi Shi, Tugba Erpek, William Headley, Bryse Flowers, George Stantchev, Zhuo Lu

Wireless systems are vulnerable to various attacks such as jamming and eavesdropping due to the shared and broadcast nature of wireless medium.

BIG-bench Machine Learning

Adversarial Deep Learning for Over-the-Air Spectrum Poisoning Attacks

no code implementations1 Nov 2019 Yalin E. Sagduyu, Yi Shi, Tugba Erpek

A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission.

QoS and Jamming-Aware Wireless Networking Using Deep Reinforcement Learning

no code implementations13 Oct 2019 Nof Abuzainab, Tugba Erpek, Kemal Davaslioglu, Yalin E. Sagduyu, Yi Shi, Sharon J. Mackey, Mitesh Patel, Frank Panettieri, Muhammad A. Qureshi, Volkan Isler, Aylin Yener

The problem of quality of service (QoS) and jamming-aware communications is considered in an adversarial wireless network subject to external eavesdropping and jamming attacks.

reinforcement-learning Reinforcement Learning (RL)

Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environments

no code implementations25 Sep 2019 Yi Shi, Kemal Davaslioglu, Yalin E. Sagduyu, William C. Headley, Michael Fowler, Gilbert Green

Dynamic spectrum access (DSA) benefits from detection and classification of interference sources including in-network users, out-network users, and jammers that may all coexist in a wireless network.

blind source separation Classification +5

IoT Network Security from the Perspective of Adversarial Deep Learning

no code implementations31 May 2019 Yalin E. Sagduyu, Yi Shi, Tugba Erpek

While there is a surge of interest to understand the security issues of machine learning, their implications have not been understood yet for wireless applications such as those in IoT systems that are susceptible to various attacks due the open and broadcast nature of wireless communications.

BIG-bench Machine Learning Information Retrieval +2

Generative Adversarial Network for Wireless Signal Spoofing

no code implementations3 May 2019 Yi Shi, Kemal Davaslioglu, Yalin E. Sagduyu

Building upon deep learning techniques, this paper introduces a spoofing attack by an adversary pair of a transmitter and a receiver that assume the generator and discriminator roles in the GAN and play a minimax game to generate the best spoofing signals that aim to fool the best trained defense mechanism.

Generative Adversarial Network

Spectrum Data Poisoning with Adversarial Deep Learning

no code implementations26 Jan 2019 Yi Shi, Tugba Erpek, Yalin E. Sagduyu, Jason H. Li

We consider the case that a cognitive transmitter senses the spectrum and transmits on idle channels determined by a machine learning algorithm.

BIG-bench Machine Learning Data Poisoning

Generative Adversarial Networks for Black-Box API Attacks with Limited Training Data

no code implementations25 Jan 2019 Yi Shi, Yalin E. Sagduyu, Kemal Davaslioglu, Jason H. Li

The exploratory attack with limited training data is shown to fail to reliably infer the target classifier of a real text classifier API that is available online to the public.

BIG-bench Machine Learning Generative Adversarial Network +1

Active Deep Learning Attacks under Strict Rate Limitations for Online API Calls

no code implementations5 Nov 2018 Yi Shi, Yalin E. Sagduyu, Kemal Davaslioglu, Jason H. Li

To mitigate the impact of limited training data, we develop an active learning approach that first builds a classifier based on a small number of API calls and uses this classifier to select samples to further collect their labels.

Active Learning BIG-bench Machine Learning +1

Deep Learning for Launching and Mitigating Wireless Jamming Attacks

no code implementations3 Jul 2018 Tugba Erpek, Yalin E. Sagduyu, Yi Shi

An adversarial machine learning approach is introduced to launch jamming attacks on wireless communications and a defense strategy is presented.

Generative Adversarial Network

Deep Supervised Hashing with Triplet Labels

1 code implementation12 Dec 2016 Xiaofang Wang, Yi Shi, Kris M. Kitani

The current state-of-the-art deep hashing method DPSH~\cite{li2015feature}, which is based on pairwise labels, performs image feature learning and hash code learning simultaneously by maximizing the likelihood of pairwise similarities.

Deep Hashing Image Retrieval

Cannot find the paper you are looking for? You can Submit a new open access paper.