Search Results for author: Hongbin Liu

Found 48 papers, 23 papers with code

Advancing Dense Endoscopic Reconstruction with Gaussian Splatting-driven Surface Normal-aware Tracking and Mapping

1 code implementation31 Jan 2025 Yiming Huang, Beilei Cui, Long Bai, Zhen Chen, Jinlin Wu, Zhen Li, Hongbin Liu, Hongliang Ren

Endo-2DTAM incorporates a surface normal-aware pipeline, which consists of tracking, mapping, and bundle adjustment modules for geometrically accurate reconstruction.

3DGS Novel View Synthesis +2

Enhancing Bronchoscopy Depth Estimation through Synthetic-to-Real Domain Adaptation

no code implementations7 Nov 2024 Qingyao Tian, Huai Liao, Xinyan Huang, Lujie Li, Hongbin Liu

Monocular depth estimation has shown promise in general imaging tasks, aiding in localization and 3D reconstruction.

3D Reconstruction Depth Prediction +3

Multi-Stage Airway Segmentation in Lung CT Based on Multi-scale Nested Residual UNet

no code implementations24 Oct 2024 Bingyu Yang, Huai Liao, Xinyan Huang, Qingyao Tian, Jinlin Wu, Jingdi Hu, Hongbin Liu

Accurate and complete segmentation of airways in chest CT images is essential for the quantitative assessment of lung diseases and the facilitation of pulmonary interventional procedures.

Image Segmentation Medical Image Segmentation +1

Making LLMs Vulnerable to Prompt Injection via Poisoning Alignment

1 code implementation18 Oct 2024 Zedian Shao, Hongbin Liu, Jaden Mu, Neil Zhenqiang Gong

In a prompt injection attack, an attacker injects a prompt into the original one, aiming to make the LLM follow the injected prompt and perform a task chosen by the attacker.

Automatically Generating Visual Hallucination Test Cases for Multimodal Large Language Models

1 code implementation15 Oct 2024 Zhongye Liu, Hongbin Liu, Yuepeng Hu, Zedian Shao, Neil Zhenqiang Gong

Our theoretical analysis shows that symmetric accuracy is an unbiased evaluation metric that remains unaffected by the imbalance of VH testing cases with varying answers when an MLLM is randomly guessing the answers, whereas traditional accuracy is prone to such imbalance.

Hallucination Large Language Model +2

Can DeepFake Speech be Reliably Detected?

no code implementations9 Oct 2024 Hongbin Liu, Youzheng Chen, Arun Narayanan, Athula Balachandran, Pedro J. Moreno, Lun Wang

Recent advances in text-to-speech (TTS) systems, particularly those with voice cloning capabilities, have made voice impersonation readily accessible, raising ethical and legal concerns due to potential misuse for malicious activities like misinformation campaigns and fraud.

Face Swapping Misinformation +2

SurgPLAN++: Universal Surgical Phase Localization Network for Online and Offline Inference

1 code implementation19 Sep 2024 Zhen Chen, Xingjian Luo, Jinlin Wu, Long Bai, Zhen Lei, Hongliang Ren, Sebastien Ourselin, Hongbin Liu

To ensure a global understanding of the surgical procedure, we devise a phase localization strategy for SurgPLAN++ to predict phase segments across the entire video through phase proposals.

Data Augmentation Offline surgical phase recognition +1

SurgTrack: CAD-Free 3D Tracking of Real-world Surgical Instruments

1 code implementation4 Sep 2024 Wenwu Guo, Jinlin Wu, Zhen Chen, Qingxiang Zhao, Miao Xu, Zhen Lei, Hongbin Liu

Compared with 2D instrument tracking methods, 3D instrument tracking has broader value in clinical practice, but is also more challenging due to weak texture, occlusion, and lack of Computer-Aided Design (CAD) models for 3D registration.

ASI-Seg: Audio-Driven Surgical Instrument Segmentation with Surgeon Intention Understanding

1 code implementation28 Jul 2024 Zhen Chen, Zongming Zhang, Wenwu Guo, Xingjian Luo, Long Bai, Jinlin Wu, Hongliang Ren, Hongbin Liu

To address these limitations in operating rooms, we propose an audio-driven surgical instrument segmentation framework, named ASI-Seg, to accurately segment the required surgical instruments by parsing the audio commands of surgeons.

Contrastive Learning Intention-oriented Segmentation +3

Refusing Safe Prompts for Multi-modal Large Language Models

1 code implementation12 Jul 2024 Zedian Shao, Hongbin Liu, Yuepeng Hu, Neil Zhenqiang Gong

In particular, our MLLM-Refusal optimizes a nearly-imperceptible refusal perturbation and adds it to an image, causing target MLLMs to likely refuse a safe prompt containing the perturbed image and a safe question.

Tracing Back the Malicious Clients in Poisoning Attacks to Federated Learning

no code implementations9 Jul 2024 Yuqi Jia, Minghong Fang, Hongbin Liu, Jinghuai Zhang, Neil Zhenqiang Gong

Existing defenses mainly focus on protecting the training phase of FL such that the learnt global model is poison free.

Federated Learning

PANS: Probabilistic Airway Navigation System for Real-time Robust Bronchoscope Localization

no code implementations8 Jul 2024 Qingyao Tian, Zhen Chen, Huai Liao, Xinyan Huang, Bingyu Yang, Lujie Li, Hongbin Liu

To overcome these challenges, we propose a novel Probabilistic Airway Navigation System (PANS), leveraging Monte-Carlo method with pose hypotheses and likelihoods to achieve robust and real-time bronchoscope localization.

SurgeMOD: Translating image-space tissue motions into vision-based surgical forces

1 code implementation25 Jun 2024 Mikel De Iturrate Reyzabal, Dionysios Malas, Shuai Wang, Sebastien Ourselin, Hongbin Liu

Using internal movements generated by natural processes like breathing or the cardiac cycle, we infer the image-space basis of the motion on the frequency domain.

Transforming Surgical Interventions with Embodied Intelligence for Ultrasound Robotics

no code implementations18 Jun 2024 Huan Xu, Jinlin Wu, Guanglin Cao, Zhen Chen, Zhen Lei, Hongbin Liu

Ultrasonography has revolutionized non-invasive diagnostic methodologies, significantly enhancing patient outcomes across various medical domains.

Motion Planning

AudioMarkBench: Benchmarking Robustness of Audio Watermarking

1 code implementation11 Jun 2024 Hongbin Liu, Moyang Guo, Zhengyuan Jiang, Lun Wang, Neil Zhenqiang Gong

The increasing realism of synthetic speech, driven by advancements in text-to-speech models, raises ethical concerns regarding impersonation and disinformation.

Benchmarking Text to Speech

VS-Assistant: Versatile Surgery Assistant on the Demand of Surgeons

no code implementations14 May 2024 Zhen Chen, Xingjian Luo, Jinlin Wu, Danny T. M. Chan, Zhen Lei, Jinqiao Wang, Sebastien Ourselin, Hongbin Liu

In this work, by leveraging advanced multimodal large language models (MLLMs), we propose a Versatile Surgery Assistant (VS-Assistant) that can accurately understand the surgeon's intention and complete a series of surgical understanding tasks, e. g., surgical scene analysis, surgical instrument detection, and segmentation on demand.

On the Federated Learning Framework for Cooperative Perception

no code implementations26 Apr 2024 Zhenrong Zhang, Jianan Liu, Xi Zhou, Tao Huang, Qing-Long Han, Jingxin Liu, Hongbin Liu

Cooperative perception is essential to enhance the efficiency and safety of future transportation systems, requiring extensive data sharing among vehicles on the road, which raises significant privacy concerns.

Autonomous Vehicles Decision Making +2

Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models

no code implementations22 Feb 2024 Hongbin Liu, Michael K. Reiter, Neil Zhenqiang Gong

However, foundation models are vulnerable to backdoor attacks and a backdoored foundation model is a single-point-of-failure of the AI ecosystem, e. g., multiple downstream classifiers inherit the backdoor vulnerabilities simultaneously.

Visual Hallucinations of Multi-modal Large Language Models

1 code implementation22 Feb 2024 Wen Huang, Hongbin Liu, Minxin Guo, Neil Zhenqiang Gong

We find that existing MLLMs such as GPT-4V, LLaVA-1. 5, and MiniGPT-v2 hallucinate for a large fraction of the instances in our benchmark.

Diversity Hallucination +2

Data Poisoning based Backdoor Attacks to Contrastive Learning

1 code implementation CVPR 2024 Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

In this work we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL.

Contrastive Learning Data Poisoning

PWISeg: Point-based Weakly-supervised Instance Segmentation for Surgical Instruments

1 code implementation16 Nov 2023 Zhen Sun, Huan Xu, Jinlin Wu, Zhen Chen, Zhen Lei, Hongbin Liu

To address this issue, we propose a novel yet effective weakly-supervised surgical instrument instance segmentation approach, named Point-based Weakly-supervised Instance Segmentation (PWISeg).

Instance Segmentation Segmentation +4

SurgPLAN: Surgical Phase Localization Network for Phase Recognition

no code implementations16 Nov 2023 Xingjian Luo, You Pang, Zhen Chen, Jinlin Wu, Zongmin Zhang, Zhen Lei, Hongbin Liu

To address these two challenges, we propose a Surgical Phase LocAlization Network, named SurgPLAN, to facilitate a more accurate and stable surgical phase recognition with the principle of temporal detection.

Surgical phase recognition

Weakly Supervised YOLO Network for Surgical Instrument Localization in Endoscopic Videos

2 code implementations23 Sep 2023 Rongfeng Wei, Jinlin Wu, Xuexue Bai, Ming Feng, Zhen Lei, Hongbin Liu, Zhen Chen

In minimally invasive surgery, surgical instrument localization is a crucial task for endoscopic videos, which enables various applications for improving surgical outcomes.

PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees

no code implementations CVPR 2023 Jinghuai Zhang, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

Existing certified defenses against adversarial point clouds suffer from a key limitation: their certified robustness guarantees are probabilistic, i. e., they produce an incorrect certified robustness guarantee with some probability.

Autonomous Driving Classification +1

Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning

no code implementations6 Dec 2022 Hongbin Liu, Wenjie Qu, Jinyuan Jia, Neil Zhenqiang Gong

In this work, we perform the first systematic, principled measurement study to understand whether and when a pre-trained encoder can address the limitations of secure or privacy-preserving supervised learning algorithms.

Data Poisoning Machine Unlearning +2

CorruptEncoder: Data Poisoning based Backdoor Attacks to Contrastive Learning

2 code implementations15 Nov 2022 Jinghuai Zhang, Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

In this work, we take the first step to analyze the limitations of existing backdoor attacks and propose new DPBAs called CorruptEncoder to CL.

Backdoor Attack Contrastive Learning +2

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning

1 code implementation25 Jul 2022 Xinlei He, Hongbin Liu, Neil Zhenqiang Gong, Yang Zhang

The results show that early stopping can mitigate the membership inference attack, but with the cost of model's utility degradation.

Data Augmentation Inference Attack +1

StolenEncoder: Stealing Pre-trained Encoders in Self-supervised Learning

1 code implementation15 Jan 2022 Yupei Liu, Jinyuan Jia, Hongbin Liu, Neil Zhenqiang Gong

A pre-trained encoder may be deemed confidential because its training requires lots of data and computation resources as well as its public release may facilitate misuse of AI, e. g., for deepfakes generation.

Self-Supervised Learning

EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning

no code implementations25 Aug 2021 Hongbin Liu, Jinyuan Jia, Wenjie Qu, Neil Zhenqiang Gong

EncoderMI can be used 1) by a data owner to audit whether its (public) data was used to pre-train an image encoder without its authorization or 2) by an attacker to compromise privacy of the training data when it is private/sensitive.

Contrastive Learning

PointGuard: Provably Robust 3D Point Cloud Classification

no code implementations CVPR 2021 Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

Our first major theoretical contribution is that we show PointGuard provably predicts the same label for a 3D point cloud when the number of adversarially modified, added, and/or deleted points is bounded.

3D Point Cloud Classification Autonomous Driving +4

Prospects of Quantum Computing for Molecular Sciences

no code implementations19 Feb 2021 Hongbin Liu, Guang Hao Low, Damian S. Steiger, Thomas Häner, Markus Reiher, Matthias Troyer

Molecular science is governed by the dynamics of electrons, atomic nuclei, and their interaction with electromagnetic fields.

Quantum Physics

Almost Tight L0-norm Certified Robustness of Top-k Predictions against Adversarial Perturbations

no code implementations ICLR 2022 Jinyuan Jia, Binghui Wang, Xiaoyu Cao, Hongbin Liu, Neil Zhenqiang Gong

For instance, our method can build a classifier that achieves a certified top-3 accuracy of 69. 2\% on ImageNet when an attacker can arbitrarily perturb 5 pixels of a testing image.

Recommendation Systems

Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected Buildings

1 code implementation3 Oct 2020 Kun Zhao, Yongkun Liu, Siyuan Hao, Shaoxing Lu, Hongbin Liu, Lijian Zhou

Instead of using visual features of the whole image directly as common image-level models based on convolutional neural networks (CNNs) do, the proposed framework firstly obtains the bounding boxes of buildings in street view images from a detector.

General Classification Image Classification

On the Intrinsic Differential Privacy of Bagging

no code implementations22 Aug 2020 Hongbin Liu, Jinyuan Jia, Neil Zhenqiang Gong

Bagging, a popular ensemble learning framework, randomly creates some subsamples of the training data, trains a base model for each subsample using a base learner, and takes majority vote among the base models when making predictions.

BIG-bench Machine Learning Ensemble Learning

Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders

no code implementations15 Aug 2017 Shan Luo, Leqi Zhu, Kaspar Althoefer, Hongbin Liu

A traditional method using handcrafted features with a shallow classifier was taken as a benchmark and the attained recognition rate was only 58. 22%.

Deep Learning Denoising +2

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