Search Results for author:
Found 113 papers, 69 papers with code
FLARE: Towards Universal Dataset Purification against Backdoor Attacks
As a result, purification methods that analyze the separation between the poisoned and benign samples in the input-output space or the final hidden layer space are less effective.
Unleashing the Power of Data Synthesis in Visual Localization
In this work, we aim to unleash the power of data synthesis to promote the generalizability of pose regression.
When Backdoors Speak: Understanding LLM Backdoor Attacks Through Model-Generated Explanations
Large Language Models (LLMs) are vulnerable to backdoor attacks, where hidden triggers can maliciously manipulate model behavior.
A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients
Evaluation metrics included token-level analysis (BLEU, ROUGE-1, ROUGE-2, ROUGE-L) and semantic similarity scores between model-generated summaries and physician-written gold standards.
NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments
Visual place recognition (VPR) enables autonomous robots to identify previously visited locations, which contributes to tasks like simultaneous localization and mapping (SLAM).
Simultaneous Localization and Mapping
Visual Place Recognition
Open World Object Detection: A Survey
Exploring new knowledge is a fundamental human ability that can be mirrored in the development of deep neural networks, especially in the field of object detection.
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
In this paper, we introduce SIREN, a novel methodology to proactively trace unauthorized data usage in black-box personalized text-to-image diffusion models.
CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction
Vision-based 3D occupancy prediction is significantly challenged by the inherent limitations of monocular vision in depth estimation.
Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training
Recent advances have been witnessed in audio-language joint learning, such as CLAP, that shows much success in multi-modal understanding tasks.
PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark
We achieve this goal by designing a scalable clean-label backdoor-based dataset watermark for point clouds that ensures both effectiveness and stealthiness.
Causal Interventional Prediction System for Robust and Explainable Effect Forecasting
Although the widespread use of AI systems in today's world is growing, many current AI systems are found vulnerable due to hidden bias and missing information, especially in the most commonly used forecasting system.
TAPI: Towards Target-Specific and Adversarial Prompt Injection against Code LLMs
To inherit the advantages of both backdoor and adversarial attacks, this paper proposes a new attack paradigm, i. e., target-specific and adversarial prompt injection (TAPI), against Code LLMs.
Improving Entity Recognition Using Ensembles of Deep Learning and Fine-tuned Large Language Models: A Case Study on Adverse Event Extraction from Multiple Sources
This study aims to evaluate the effectiveness of LLMs and traditional deep learning models in AE extraction, and to assess the impact of ensembling these models on performance.
Tell Me Where You Are: Multimodal LLMs Meet Place Recognition
Our key design is to use vision-based retrieval to propose several candidates and then leverage language-based reasoning to carefully inspect each candidate for a final decision.
Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset
More specifically, MARS is collected with a fleet of autonomous vehicles driving within a certain geographical area.
Memorize What Matters: Emergent Scene Decomposition from Multitraverse
Humans naturally retain memories of permanent elements, while ephemeral moments often slip through the cracks of memory.
FedSheafHN: Personalized Federated Learning on Graph-structured Data
Personalized subgraph Federated Learning (FL) is a task that customizes Graph Neural Networks (GNNs) to individual client needs, accommodating diverse data distributions.
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
Current methods predominantly rely on LiDAR or camera inputs for 3D occupancy prediction.
Nearest is Not Dearest: Towards Practical Defense against Quantization-conditioned Backdoor Attacks
Model quantization is widely used to compress and accelerate deep neural networks.
BadActs: A Universal Backdoor Defense in the Activation Space
Backdoor attacks pose an increasingly severe security threat to Deep Neural Networks (DNNs) during their development stage.
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transformers
The experiments on diverse visual recognition tasks confirm the success of our switchable backdoor attack, i. e., achieving 95%+ attack success rate, and also being hard to be detected and removed.
IBD-PSC: Input-level Backdoor Detection via Parameter-oriented Scaling Consistency
Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries can maliciously trigger model misclassifications by implanting a hidden backdoor during model training.
Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution
Motivated by this understanding, we design a new watermarking paradigm, $i. e.$, Explanation as a Watermark (EaaW), that implants verification behaviors into the explanation of feature attribution instead of model predictions.
Relation Extraction Using Large Language Models: A Case Study on Acupuncture Point Locations
This study underscores the effectiveness of LLMs like GPT in extracting relations related to acupoint locations, with implications for accurately modeling acupuncture knowledge and promoting standard implementation in acupuncture training and practice.
Which Model Generated This Image? A Model-Agnostic Approach for Origin Attribution
In this work, we study the origin attribution of generated images in a practical setting where only a few images generated by a source model are available and the source model cannot be accessed.
ActFormer: Scalable Collaborative Perception via Active Queries
This proactive understanding of the visual features' relevance does not require the transmission of the features themselves, enhancing both communication and computation efficiency.
The First Place Solution of WSDM Cup 2024: Leveraging Large Language Models for Conversational Multi-Doc QA
Conversational multi-doc question answering aims to answer specific questions based on the retrieved documents as well as the contextual conversations.
A Survey of Privacy Threats and Defense in Vertical Federated Learning: From Model Life Cycle Perspective
Vertical Federated Learning (VFL) is a federated learning paradigm where multiple participants, who share the same set of samples but hold different features, jointly train machine learning models.
Multi-modality action recognition based on dual feature shift in vehicle cabin monitoring
Driver Action Recognition (DAR) is crucial in vehicle cabin monitoring systems.
Not All Prompts Are Secure: A Switchable Backdoor Attack Against Pre-trained Vision Transfomers
The experiments on diverse visual recognition tasks confirm the success of our switchable backdoor attack i. e. achieving 95%+ attack success rate and also being hard to be detected and removed.
Geo2SigMap: High-Fidelity RF Signal Mapping Using Geographic Databases
First, we develop an automated framework that seamlessly integrates three open-source tools: OpenStreetMap (geographic databases), Blender (computer graphics), and Sionna (ray tracing), enabling the efficient generation of large-scale 3D building maps and ray tracing models.
Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger
We argue that the intensity constraint of existing SSBAs is mostly because their trigger patterns are `content-irrelevant' and therefore act as `noises' for both humans and DNNs.
LiDAR-based 4D Occupancy Completion and Forecasting
In this paper, we introduce a novel LiDAR perception task of Occupancy Completion and Forecasting (OCF) in the context of autonomous driving to unify these aspects into a cohesive framework.
MonoGAE: Roadside Monocular 3D Object Detection with Ground-Aware Embeddings
We discover that most existing monocular 3D object detectors rely on the ego-vehicle prior assumption that the optical axis of the camera is parallel to the ground.
AE-GPT: Using Large Language Models to Extract Adverse Events from Surveillance Reports-A Use Case with Influenza Vaccine Adverse Events
Though Vaccines are instrumental in global health, mitigating infectious diseases and pandemic outbreaks, they can occasionally lead to adverse events (AEs).
Semi-supervised Sound Event Detection with Local and Global Consistency Regularization
Then, the local consistency is adopted to encourage the model to leverage local features for frame-level predictions, and the global consistency is applied to force features to align with global prototypes through a specially designed contrastive loss.
Audio-free Prompt Tuning for Language-Audio Models
Contrastive Language-Audio Pretraining (CLAP) is pre-trained to associate audio features with human language, making it a natural zero-shot classifier to recognize unseen sound categories.
Towards Robust Model Watermark via Reducing Parametric Vulnerability
To protect the copyright of DNNs, backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model by embedding a specific backdoor behavior before releasing it.
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs.
One-bit Flip is All You Need: When Bit-flip Attack Meets Model Training
We propose a training-assisted bit flip attack, in which the adversary is involved in the training stage to build a high-risk model to release.
Towards Stealthy Backdoor Attacks against Speech Recognition via Elements of Sound
Motivated by these findings, we propose to exploit elements of sound ($e. g.$, pitch and timbre) to design more stealthy yet effective poison-only backdoor attacks.
SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving
Monocular scene understanding is a foundational component of autonomous systems.
3D Semantic Scene Completion
3D Semantic Scene Completion from a single 2D image
Backdoor Attack with Sparse and Invisible Trigger
More importantly, it is not feasible to simply combine existing methods to design an effective sparse and invisible backdoor attack.
Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation
MOT-CUP demonstrates the importance of uncertainty quantification in both COD and MOT, and provides the first attempt to improve the accuracy and reduce the uncertainty in MOT based on COD through uncertainty propagation.
Among Us: Adversarially Robust Collaborative Perception by Consensus
This leads to our hypothesize-and-verify framework: perception results with and without collaboration from a random subset of teammates are compared until reaching a consensus.
Defending Against Backdoor Attacks by Layer-wise Feature Analysis
We find out that the feature difference between benign and poisoned samples tends to be maximum at a critical layer, which is not always the one typically used in existing defenses, namely the layer before fully-connected layers.
VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
To enable such capability in AI systems, we propose VoxFormer, a Transformer-based semantic scene completion framework that can output complete 3D volumetric semantics from only 2D images.
3D geometry
3D Semantic Scene Completion from a single RGB image
+1
Revisiting the Assumption of Latent Separability for Backdoor Defenses
This latent separation is so pervasive that a family of backdoor defenses directly take it as a default assumption (dubbed latent separability assumption), based on which to identify poison samples via cluster analysis in the latent space.
BackdoorBox: A Python Toolbox for Backdoor Learning
Third-party resources ($e. g.$, samples, backbones, and pre-trained models) are usually involved in the training of deep neural networks (DNNs), which brings backdoor attacks as a new training-phase threat.
Metabolomics of Aging and Alzheimer's Disease: From Single-Omics to Multi-Omics
Aging is a multifactorial process and a key factor of morbidity and mortality.
DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization
LiDAR mapping is important yet challenging in self-driving and mobile robotics.
PVT++: A Simple End-to-End Latency-Aware Visual Tracking Framework
Visual object tracking is essential to intelligent robots.
Backdoor Defense via Suppressing Model Shortcuts
Recent studies have demonstrated that deep neural networks (DNNs) are vulnerable to backdoor attacks during the training process.
BATT: Backdoor Attack with Transformation-based Triggers
The backdoor adversaries intend to maliciously control the predictions of attacked DNNs by injecting hidden backdoors that can be activated by adversary-specified trigger patterns during the training process.
Untargeted Backdoor Attack against Object Detection
The backdoored model has promising performance in predicting benign samples, whereas its predictions can be maliciously manipulated by adversaries based on activating its backdoors with pre-defined trigger patterns.
A Hybrid System of Sound Event Detection Transformer and Frame-wise Model for DCASE 2022 Task 4
For the frame-wise model, the ICT-TOSHIBA system of DCASE 2021 Task 4 is used.
Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection
In this paper, we revisit dataset ownership verification.
Uncertainty Quantification of Collaborative Detection for Self-Driving
Our work is the first to estimate the uncertainty of collaborative object detection.
Self-Supervised Place Recognition by Refining Temporal and Featural Pseudo Labels from Panoramic Data
Inspired by noisy label learning, we propose a novel self-supervised framework named TF-VPR that uses temporal neighborhoods and learnable feature neighborhoods to discover unknown spatial neighborhoods.
Adaptive Local Implicit Image Function for Arbitrary-scale Super-resolution
Image representation is critical for many visual tasks.
Black-box Dataset Ownership Verification via Backdoor Watermarking
The rapid development of DNNs has benefited from the existence of some high-quality datasets ($e. g.$, ImageNet), which allow researchers and developers to easily verify the performance of their methods.
MOVE: Effective and Harmless Ownership Verification via Embedded External Features
In general, we conduct the ownership verification by verifying whether a suspicious model contains the knowledge of defender-specified external features.
Enhanced Atmospheric Turbulence Resiliency with Successive Interference Cancellation DSP in Mode Division Multiplexing Free-Space Optical Links
We experimentally demonstrate the enhanced atmospheric turbulence resiliency in a 137. 8 Gbit/s/mode mode-division multiplexing free-space optical communication link through the application of a successive interference cancellation digital signal processing algorithm.
Circumventing Backdoor Defenses That Are Based on Latent Separability
This latent separation is so pervasive that a family of backdoor defenses directly take it as a default assumption (dubbed latent separability assumption), based on which to identify poison samples via cluster analysis in the latent space.
Egocentric Prediction of Action Target in 3D
We are interested in anticipating as early as possible the target location of a person's object manipulation action in a 3D workspace from egocentric vision.
Deep Convolutional Neural Networks for Molecular Subtyping of Gliomas Using Magnetic Resonance Imaging
Methods: A DCNN model was developed for the prediction of the five glioma subtypes based on a hierarchical classification paradigm.
V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving
Vehicle-to-everything (V2X) communication techniques enable the collaboration between vehicles and many other entities in the neighboring environment, which could fundamentally improve the perception system for autonomous driving.
Backdoor Defense via Decoupling the Training Process
Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples.
Few-Shot Backdoor Attacks on Visual Object Tracking
Visual object tracking (VOT) has been widely adopted in mission-critical applications, such as autonomous driving and intelligent surveillance systems.
Dynamic Scene Graph Generation via Anticipatory Pre-Training
Humans can not only see the collection of objects in visual scenes, but also identify the relationship between objects.
Defending against Model Stealing via Verifying Embedded External Features
In this paper, we explore the defense from another angle by verifying whether a suspicious model contains the knowledge of defender-specified \emph{external features}.
CRLB Approaching Pilot-aided Phase and Channel Estimation Algorithm in MIMO Systems with Phase Noise and Quasi-Static Channel Fading
Our numerical results show that the performance of our phase estimation algorithm is close to the proposed CRLB.
SNPs Filtered by Allele Frequency Improve the Prediction of Hypertension Subtypes
Hypertension is the leading global cause of cardiovascular disease and premature death.
Learning Distilled Collaboration Graph for Multi-Agent Perception
Our approach is validated on V2X-Sim 1. 0, a large-scale multi-agent perception dataset that we synthesized using CARLA and SUMO co-simulation.
Ranked #3 on
3D Object Detection
on V2X-SIM
Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non-Contrast CT Images
In this paper, we propose a symmetry enhanced attention network (SEAN) for acute ischemic infarct segmentation.
Regional Adversarial Training for Better Robust Generalization
Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks.
Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation
In a unified framework, we jointly predict the feasible 6-DoF grasp poses, instance semantic segmentation, and collision information.
HiFT: Hierarchical Feature Transformer for Aerial Tracking
Most existing Siamese-based tracking methods execute the classification and regression of the target object based on the similarity maps.
Asymptotic analysis of V-BLAST MIMO for coherent optical wireless communications in Gamma-Gamma turbulence
This paper investigates the asymptotic BER performance of coherent optical wireless communication systems in Gamma-Gamma turbulence when applying the V-BLAST MIMO scheme.
SiamAPN++: Siamese Attentional Aggregation Network for Real-Time UAV Tracking
By virtue of the attention mechanism, we conduct a special attentional aggregation network (AAN) consisting of self-AAN and cross-AAN for raising the representation ability of features eventually.
Backdoor Attack in the Physical World
We demonstrate that this attack paradigm is vulnerable when the trigger in testing images is not consistent with the one used for training.
Fooling LiDAR Perception via Adversarial Trajectory Perturbation
LiDAR point clouds collected from a moving vehicle are functions of its trajectories, because the sensor motion needs to be compensated to avoid distortions.
Predictive Visual Tracking: A New Benchmark and Baseline Approach
As a crucial robotic perception capability, visual tracking has been intensively studied recently.
Hidden Backdoor Attack against Semantic Segmentation Models
Deep neural networks (DNNs) are vulnerable to the \emph{backdoor attack}, which intends to embed hidden backdoors in DNNs by poisoning training data.
An Optimized H.266/VVC Software Decoder On Mobile Platform
As the successor of H. 265/HEVC, the new versatile video coding standard (H. 266/VVC) can provide up to 50% bitrate saving with the same subjective quality, at the cost of increased decoding complexity.
Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bits
By utilizing the latest technique in integer programming, we equivalently reformulate this BIP problem as a continuous optimization problem, which can be effectively and efficiently solved using the alternating direction method of multipliers (ADMM) method.
Multidimensional Information Assisted Deep Learning Realizing Flexible Recognition of Vortex Beam Modes
Recognition of OAM modes unlimited by distance and sign of TC achieved by MIADLFR method can make optical communication and detection by OAM light much more attractive.
Optics Image and Video Processing Medical Physics
Siamese Anchor Proposal Network for High-Speed Aerial Tracking
In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency.
Backdoor Attack against Speaker Verification
We also demonstrate that existing backdoor attacks cannot be directly adopted in attacking speaker verification.
Open-sourced Dataset Protection via Backdoor Watermarking
Based on the proposed backdoor-based watermarking, we use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model of the benign samples and their correspondingly watermarked samples ($i. e.$, images with trigger) on the target class.
GTEA: Inductive Representation Learning on Temporal Interaction Graphs via Temporal Edge Aggregation
In this paper, we propose the Graph Temporal Edge Aggregation (GTEA) framework for inductive learning on Temporal Interaction Graphs (TIGs).
Rectified Decision Trees: Exploring the Landscape of Interpretable and Effective Machine Learning
Interpretability and effectiveness are two essential and indispensable requirements for adopting machine learning methods in reality.
DR^2Track: Towards Real-Time Visual Tracking for UAV via Distractor Repressed Dynamic Regression
By repressing the response of distractors in the regressor learning, we can dynamically and adaptively alter our regression target to leverage the tracking robustness as well as adaptivity.
Automatic Failure Recovery and Re-Initialization for Online UAV Tracking with Joint Scale and Aspect Ratio Optimization
Current unmanned aerial vehicle (UAV) visual tracking algorithms are primarily limited with respect to: (i) the kind of size variation they can deal with, (ii) the implementation speed which hardly meets the real-time requirement.
Towards Robust Visual Tracking for Unmanned Aerial Vehicle with Tri-Attentional Correlation Filters
Object tracking has been broadly applied in unmanned aerial vehicle (UAV) tasks in recent years.
Backdoor Learning: A Survey
Backdoor attack intends to embed hidden backdoor into deep neural networks (DNNs), so that the attacked models perform well on benign samples, whereas their predictions will be maliciously changed if the hidden backdoor is activated by attacker-specified triggers.
Context-Aware Refinement Network Incorporating Structural Connectivity Prior for Brain Midline Delineation
Nevertheless, there are still great challenges with brain midline delineation, such as the largely deformed midline caused by the mass effect and the possible morphological failure that the predicted midline is not a connected curve.
Targeted Attack for Deep Hashing based Retrieval
In this paper, we propose a novel method, dubbed deep hashing targeted attack (DHTA), to study the targeted attack on such retrieval.
Rethinking the Trigger of Backdoor Attack
Backdoor attack intends to inject hidden backdoor into the deep neural networks (DNNs), such that the prediction of the infected model will be maliciously changed if the hidden backdoor is activated by the attacker-defined trigger, while it performs well on benign samples.
AutoTrack: Towards High-Performance Visual Tracking for UAV with Automatic Spatio-Temporal Regularization
Considerable tests in the indoor practical scenarios have proven the effectiveness and versatility of our localization method.
Toward Adversarial Robustness via Semi-supervised Robust Training
In this work, we propose a novel defense method, the robust training (RT), by jointly minimizing two separated risks ($R_{stand}$ and $R_{rob}$), which is with respect to the benign example and its neighborhoods respectively.
Training-Set Distillation for Real-Time UAV Object Tracking
After the establishment of a new slot, the weighted fusion of the previous samples generates one key-sample, in order to reduce the number of samples to be scored.
Keyfilter-Aware Real-Time UAV Object Tracking
Correlation filter-based tracking has been widely applied in unmanned aerial vehicle (UAV) with high efficiency.
Globally Guided Progressive Fusion Network for 3D Pancreas Segmentation
Recently 3D volumetric organ segmentation attracts much research interest in medical image analysis due to its significance in computer aided diagnosis.
Visual Privacy Protection via Mapping Distortion
To a large extent, the privacy of visual classification data is mainly in the mapping between the image and its corresponding label, since this relation provides a great amount of information and can be used in other scenarios.
Adversarial Defense via Local Flatness Regularization
In this paper, we define the local flatness of the loss surface as the maximum value of the chosen norm of the gradient regarding to the input within a neighborhood centered on the benign sample, and discuss the relationship between the local flatness and adversarial vulnerability.
Augmented Memory for Correlation Filters in Real-Time UAV Tracking
The outstanding computational efficiency of discriminative correlation filter (DCF) fades away with various complicated improvements.
Boundary Effect-Aware Visual Tracking for UAV with Online Enhanced Background Learning and Multi-Frame Consensus Verification
Meanwhile, convolutional features are extracted to provide a more comprehensive representation of the object.
Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking
Traditional framework of discriminative correlation filters (DCF) is often subject to undesired boundary effects.
$t$-$k$-means: A Robust and Stable $k$-means Variant
$k$-means algorithm is one of the most classical clustering methods, which has been widely and successfully used in signal processing.
Rectified Decision Trees: Towards Interpretability, Compression and Empirical Soundness
How to obtain a model with good interpretability and performance has always been an important research topic.
Multinomial Random Forest: Toward Consistency and Privacy-Preservation
Despite the impressive performance of random forests (RF), its theoretical properties have not been thoroughly understood.
Semi-Supervised Brain Lesion Segmentation with an Adapted Mean Teacher Model
Since unannotated data is generally abundant, it is desirable to use unannotated data to improve the segmentation performance for CNNs when limited annotated data is available.
