Search Results for author:
Found 81 papers, 19 papers with code
Efficiently Adversarial Examples Generation for Visual-Language Models under Targeted Transfer Scenarios using Diffusion Models
Specifically, AdvDiffVLM employs Adaptive Ensemble Gradient Estimation to modify the score during the diffusion model's reverse generation process, ensuring the adversarial examples produced contain natural adversarial semantics and thus possess enhanced transferability.
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest.
Light the Night: A Multi-Condition Diffusion Framework for Unpaired Low-Light Enhancement in Autonomous Driving
Vision-centric perception systems for autonomous driving have gained considerable attention recently due to their cost-effectiveness and scalability, especially compared to LiDAR-based systems.
CosalPure: Learning Concept from Group Images for Robust Co-Saliency Detection
In this paper, we propose a novel robustness enhancement framework by first learning the concept of the co-salient objects based on the input group images and then leveraging this concept to purify adversarial perturbations, which are subsequently fed to CoSODs for robustness enhancement.
Boosting Transferability in Vision-Language Attacks via Diversification along the Intersection Region of Adversarial Trajectory
Vision-language pre-training (VLP) models exhibit remarkable capabilities in comprehending both images and text, yet they remain susceptible to multimodal adversarial examples (AEs).
Your Large Language Model is Secretly a Fairness Proponent and You Should Prompt it Like One
Building on this insight and observation, we develop FairThinking, a pipeline designed to automatically generate roles that enable LLMs to articulate diverse perspectives for fair expressions.
Purifying Large Language Models by Ensembling a Small Language Model
The emerging success of large language models (LLMs) heavily relies on collecting abundant training data from external (untrusted) sources.
FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distribution
To expose this potential vulnerability, we aim to build an adversarial attack forcing SDEdit to generate a specific data distribution aligned with a specified attribute (e. g., female), without changing the input's attribute characteristics.
Transductive Reward Inference on Graph
In this study, we present a transductive inference approach on that reward information propagation graph, which enables the effective estimation of rewards for unlabelled data in offline reinforcement learning.
Improving Robustness of LiDAR-Camera Fusion Model against Weather Corruption from Fusion Strategy Perspective
In recent years, LiDAR-camera fusion models have markedly advanced 3D object detection tasks in autonomous driving.
AdvGPS: Adversarial GPS for Multi-Agent Perception Attack
The multi-agent perception system collects visual data from sensors located on various agents and leverages their relative poses determined by GPS signals to effectively fuse information, mitigating the limitations of single-agent sensing, such as occlusion.
Spy-Watermark: Robust Invisible Watermarking for Backdoor Attack
Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data.
Leveraging Open-Vocabulary Diffusion to Camouflaged Instance Segmentation
Such cross-domain representations are desirable in segmenting camouflaged objects where visual cues are subtle to distinguish the objects from the background, especially in segmenting novel objects which are not seen in training.
C-NERF: Representing Scene Changes as Directional Consistency Difference-based NeRF
Our approach surpasses state-of-the-art 2D change detection and NeRF-based methods by a significant margin.
TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation
At the second stage, the pixels are divided into different branches based on their transferable property which is dependent on Kullback-Leibler divergence.
IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
The underlying rationale behind our idea is that image resampling can alleviate the influence of adversarial perturbations while preserving essential semantic information, thereby conferring an inherent advantage in defending against adversarial attacks.
SAIR: Learning Semantic-aware Implicit Representation
To this end, we propose a framework with two modules: (1) building a semantic implicit representation (SIR) for a corrupted image whose large regions miss.
BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout
To this end, we propose a two-stage generative method, dubbed BEVControl, that can generate accurate foreground and background contents.
CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification
Using the aggregated similarity scores as the initial pseudo labels at the training stage, we propose an optimization framework to train the parameters of the classification network and refine pseudo labels for unobserved labels.
SuperInpaint: Learning Detail-Enhanced Attentional Implicit Representation for Super-resolutional Image Inpainting
Given the coordinates of a pixel we want to reconstruct, we first collect its neighboring pixels in the input image and extract their detail-enhanced semantic embeddings, unmask-attentional semantic embeddings, importance values, and spatial distances to the desired pixel.
CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields
Neural Radiance Fields (NeRF) have the potential to be a major representation of media.
CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion
In this paper, we propose Cross-View Synthesis Transformer (CVSformer), which consists of Multi-View Feature Synthesis and Cross-View Transformer for learning cross-view object relationships.
Defense against Adversarial Cloud Attack on Remote Sensing Salient Object Detection
Furthermore, we design DefenseNet as a learn-able pre-processing to the adversarial cloudy images so as to preserve the performance of the deep learning based remote sensing SOD model, without tuning the already deployed deep SOD model.
FAIRER: Fairness as Decision Rationale Alignment
Existing fairness regularization terms fail to achieve decision rationale alignment because they only constrain last-layer outputs while ignoring intermediate neuron alignment.
RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection
The emergence of different sensors (Near-Infrared, Depth, etc.)
On the Robustness of Segment Anything
Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness.
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, they also present an exploitable avenue for high accessible backdoor attacks.
Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches
The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e. g., autonomous driving, content moderation, biometric authentication, medical imaging) in the physical world.
Learning Restoration is Not Enough: Transfering Identical Mapping for Single-Image Shadow Removal
State-of-the-art shadow removal methods train deep neural networks on collected shadow & shadow-free image pairs, which are desired to complete two distinct tasks via shared weights, i. e., data restoration for shadow regions and identical mapping for non-shadow regions.
Evading DeepFake Detectors via Adversarial Statistical Consistency
Second, we find that the statistical differences between natural and DeepFake images are positively associated with the distribution shifting between the two kinds of images, and we propose to use a distribution-aware loss to guide the optimization of different degradations.
FedSDG-FS: Efficient and Secure Feature Selection for Vertical Federated Learning
Vertical Federated Learning (VFL) enables multiple data owners, each holding a different subset of features about largely overlapping sets of data sample(s), to jointly train a useful global model.
Leveraging Inpainting for Single-Image Shadow Removal
In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly: a naive encoder-decoder network gets competitive restoration quality w. r. t.
Structure-Informed Shadow Removal Networks
Hence, in this paper, we propose to remove shadows at the image structure level.
Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition
Existing results in [9, 20, 25, 36] have indicated that, as the frontal component of the overall model, the spatial perception module used for spatial feature extraction tends to be insufficiently trained.
Ranked #4 on
Sign Language Recognition
on CSL-Daily
Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape
As a result, backdoor pattern designed for one certain 3D data structure will be disable for other data structures of the same 3D scene.
Background-Mixed Augmentation for Weakly Supervised Change Detection
Change detection (CD) is to decouple object changes (i. e., object missing or appearing) from background changes (i. e., environment variations) like light and season variations in two images captured in the same scene over a long time span, presenting critical applications in disaster management, urban development, etc.
Coarse-to-fine Task-driven Inpainting for Geoscience Images
To the best of our knowledge, all the existing image inpainting algorithms learn to repair the occluded regions for a better visualization quality, they are excellent for natural images but not good enough for geoscience images by ignoring the geoscience related tasks.
Common Corruption Robustness of Point Cloud Detectors: Benchmark and Enhancement
Then, for the first attempt, we construct a benchmark based on the physical-aware common corruptions for point cloud detectors, which contains a total of 1, 122, 150 examples covering 7, 481 scenes, 25 common corruption types, and 6 severities.
DARTSRepair: Core-failure-set Guided DARTS for Network Robustness to Common Corruptions
Then, we propose a novel core-failure-set guided DARTS that embeds a K-center-greedy algorithm for DARTS to select suitable corrupted failure examples to refine the model architecture.
IDET: Iterative Difference-Enhanced Transformers for High-Quality Change Detection
Change detection (CD) aims to detect change regions within an image pair captured at different times, playing a significant role in diverse real-world applications.
Single Object Tracking Research: A Survey
Visual object tracking is an important task in computer vision, which has many real-world applications, e. g., video surveillance, visual navigation.
NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks
Inspired by software testing, a number of structural coverage criteria are designed and proposed to measure the test adequacy of DNNs.
MISF: Multi-level Interactive Siamese Filtering for High-Fidelity Image Inpainting
As a result, the final method takes the advantage of effective semantic & image-level filling for high-fidelity inpainting.
Masked Faces with Faced Masks
Modern face recognition systems (FRS) still fall short when the subjects are wearing facial masks, a common theme in the age of respiratory pandemics.
ALA: Naturalness-aware Adversarial Lightness Attack
To obtain adversarial examples with a high attack success rate, we propose unconstrained enhancement in terms of the light and shade relationship in images.
Uncertainty-Aware Cascaded Dilation Filtering for High-Efficiency Deraining
First, we propose the uncertainty-aware cascaded predictive filtering (UC-PFilt) that can identify the difficulties of reconstructing clean pixels via predicted kernels and remove the residual rain traces effectively.
Benchmarking Shadow Removal for Facial Landmark Detection and Beyond
The observation of this work motivates us to design a novel detection-aware shadow removal framework, which empowers shadow removal to achieve higher restoration quality and enhance the shadow robustness of deployed facial landmark detectors.
ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks
In this work, as the first attempt, we initiate to repair DNNs by jointly optimizing the architecture and weights at a higher (i. e., block) level.
Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network
Bokeh effect is a natural shallow depth-of-field phenomenon that blurs the out-of-focus part in photography.
Adversarial Relighting Against Face Recognition
To this end, we first propose the physical modelbased adversarial relighting attack (ARA) denoted as albedoquotient-based adversarial relighting attack (AQ-ARA).
CarveNet: Carving Point-Block for Complex 3D Shape Completion
3D point cloud completion is very challenging because it heavily relies on the accurate understanding of the complex 3D shapes (e. g., high-curvature, concave/convex, and hollowed-out 3D shapes) and the unknown & diverse patterns of the partially available point clouds.
Learning to Adversarially Blur Visual Object Tracking
In this work, we explore the robustness of visual object trackers against motion blur from a new angle, i. e., adversarial blur attack (ABA).
AdvFilter: Predictive Perturbation-aware Filtering against Adversarial Attack via Multi-domain Learning
To this end, we first comprehensively investigate two kinds of pixel denoising methods for adversarial robustness enhancement (i. e., existing additive-based and unexplored filtering-based methods) under the loss functions of image-level and semantic-level, respectively, showing that pixel-wise filtering can obtain much higher image quality (e. g., higher PSNR) as well as higher robustness (e. g., higher accuracy on adversarial examples) than existing pixel-wise additive-based method.
JPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting
In this paper, for the first time, we formulate image inpainting as a mix of two problems, predictive filtering and deep generation.
Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
Successful applications of InfoNCE and its variants have popularized the use of contrastive variational mutual information (MI) estimators in machine learning.
Simpler, Faster, Stronger: Breaking The log-K Curse On Contrastive Learners With FlatNCE
InfoNCE-based contrastive representation learners, such as SimCLR, have been tremendously successful in recent years.
Sparta: Spatially Attentive and Adversarially Robust Activation
In both cases, Sparta leads to CNNs with higher robustness than the vanilla ReLU, verifying the flexibility and versatility of the proposed method.
AVA: Adversarial Vignetting Attack against Visual Recognition
Moreover, we propose the geometry-aware level-set optimization method to solve the adversarial vignetting regions and physical parameters jointly.
Let There be Light: Improved Traffic Surveillance via Detail Preserving Night-to-Day Transfer
As one of the state-of-the-art perception approaches, detecting the interested objects in each frame of video surveillance is widely desired by ITS.
AdvHaze: Adversarial Haze Attack
We also visualize the correlation matrices, which inspire us to jointly apply different perturbations to improve the success rate of the attack.
DeepMix: Online Auto Data Augmentation for Robust Visual Object Tracking
Online updating of the object model via samples from historical frames is of great importance for accurate visual object tracking.
Auto-Exposure Fusion for Single-Image Shadow Removal
We conduct extensive experiments on the ISTD, ISTD+, and SRD datasets to validate our method's effectiveness and show better performance in shadow regions and comparable performance in non-shadow regions over the state-of-the-art methods.
Countering Malicious DeepFakes: Survey, Battleground, and Horizon
To fill this gap, in this paper, we provide a comprehensive overview and detailed analysis of the research work on the topic of DeepFake generation, DeepFake detection as well as evasion of DeepFake detection, with more than 318 research papers carefully surveyed.
Sparta: Spatially Attentive and Adversarially Robust Activations
Moreover, comprehensive evaluations have demonstrated two important properties of our method: First, superior transferability across DNNs.
DeepRepair: Style-Guided Repairing for DNNs in the Real-world Operational Environment
In this paper, we propose a style-guided data augmentation for repairing DNN in the operational environment.
Dodging DeepFake Detection via Implicit Spatial-Domain Notch Filtering
We first demonstrate that frequency-domain notch filtering, although famously shown to be effective in removing periodic noise in the spatial domain, is infeasible for our task at hand due to the manual designs required for the notch filters.
Bias Field Poses a Threat to DNN-based X-Ray Recognition
Our method reveals the potential threat to the DNN-based X-ray automated diagnosis and can definitely benefit the development of bias-field-robust automated diagnosis system.
Adversarial Rain Attack and Defensive Deraining for DNN Perception
To defend the DNNs from the negative rain effect, we also present a defensive deraining strategy, for which we design an adversarial rain augmentation that uses mixed adversarial rain layers to enhance deraining models for downstream DNN perception.
Can You Spot the Chameleon? Adversarially Camouflaging Images from Co-Salient Object Detection
In this paper, we address this problem from the perspective of adversarial attacks and identify a novel task: adversarial co-saliency attack.
EfficientDeRain: Learning Pixel-wise Dilation Filtering for High-Efficiency Single-Image Deraining
To fill this gap, in this paper, we regard the single-image deraining as a general image-enhancing problem and originally propose a model-free deraining method, i. e., EfficientDeRain, which is able to process a rainy image within 10~ms (i. e., around 6~ms on average), over 80 times faster than the state-of-the-art method (i. e., RCDNet), while achieving similar de-rain effects.
Adversarial Exposure Attack on Diabetic Retinopathy Imagery
In this paper, we study this problem from the viewpoint of adversarial attack and identify a totally new task, i. e., adversarial exposure attack generating adversarial images by tuning image exposure to mislead the DNNs with significantly high transferability.
Pasadena: Perceptually Aware and Stealthy Adversarial Denoise Attack
To this end, we initiate the very first attempt to study this problem from the perspective of adversarial attack and propose the adversarial denoise attack.
FakePolisher: Making DeepFakes More Detection-Evasive by Shallow Reconstruction
At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image.
DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms
As the GAN-based face image and video generation techniques, widely known as DeepFakes, have become more and more matured and realistic, there comes a pressing and urgent demand for effective DeepFakes detectors.
Watch out! Motion is Blurring the Vision of Your Deep Neural Networks
Besides, the attack is further enhanced by adaptively tuning the translations of object and background.
FakeLocator: Robust Localization of GAN-Based Face Manipulations
In this work, we investigate the architecture of existing GAN-based face manipulation methods and observe that the imperfection of upsampling methods therewithin could be served as an important asset for GAN-synthesized fake image detection and forgery localization.
Amora: Black-box Adversarial Morphing Attack
In this paper, we investigate and introduce a new type of adversarial attack to evade FR systems by manipulating facial content, called \textbf{\underline{a}dversarial \underline{mor}phing \underline{a}ttack} (a. k. a.
SPARK: Spatial-aware Online Incremental Attack Against Visual Tracking
We identify that online object tracking poses two new challenges: 1) it is difficult to generate imperceptible perturbations that can transfer across frames, and 2) real-time trackers require the attack to satisfy a certain level of efficiency.
Research Commentary on Recommendations with Side Information: A Survey and Research Directions
This Research Commentary aims to provide a comprehensive and systematic survey of the recent research on recommender systems with side information.
Effects of Blur and Deblurring to Visual Object Tracking
In this paper, we address these two problems by constructing a Blurred Video Tracking benchmark, which contains a variety of videos with different levels of motion blurs, as well as ground truth tracking results for evaluating trackers.
Learning Dynamic Siamese Network for Visual Object Tracking
How to effectively learn temporal variation of target appearance, to exclude the interference of cluttered background, while maintaining real-time response, is an essential problem of visual object tracking.
Ranked #5 on
Visual Object Tracking
on OTB-2013
