Search Results for author:
Found 25 papers, 4 papers with code
Towards more transferable adversarial attack in black-box manner
Traditional black-box methods have generally focused on improving the optimization framework (e. g., utilizing momentum in MI-FGSM) to enhance transferability, rather than examining the dependency on surrogate white-box model architectures.
My Face Is Mine, Not Yours: Facial Protection Against Diffusion Model Face Swapping
The proliferation of diffusion-based deepfake technologies poses significant risks for unauthorized and unethical facial image manipulation.
Combining Clusters for the Approximate Randomization Test
In this paper, I develop computationally efficient procedures to combine clusters when this identification requirement does not hold.
T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting
To address this challenge, we propose a Hierarchical Semantic Correction Module that progressively refines text-image feature alignment, and a Representational Regional Coherence Loss that provides reliable supervision signals by leveraging the cross-attention maps extracted from the denoising U-Net.
MMAD-Purify: A Precision-Optimized Framework for Efficient and Scalable Multi-Modal Attacks
With the rise of multimodality, diffusion models have emerged as powerful tools not only for generative tasks but also for various applications such as image editing, inpainting, and super-resolution.
Instant Adversarial Purification with Adversarial Consistency Distillation
Neural networks, despite their remarkable performance in widespread applications, including image classification, are also known to be vulnerable to subtle adversarial noise.
Sensitivity Analysis for Dynamic Discrete Choice Models
This paper proposes two sensitivity analysis procedures for dynamic discrete choice models with respect to the fixed parameters.
A Grey-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse
Recent advancements in generative AI, particularly Latent Diffusion Models (LDMs), have revolutionized image synthesis and manipulation.
Instruct2Attack: Language-Guided Semantic Adversarial Attacks
We propose Instruct2Attack (I2A), a language-guided semantic attack that generates semantically meaningful perturbations according to free-form language instructions.
Whole-body Detection, Recognition and Identification at Altitude and Range
In this paper, we address the challenging task of whole-body biometric detection, recognition, and identification at distances of up to 500m and large pitch angles of up to 50 degree.
Distillation-guided Representation Learning for Unconstrained Gait Recognition
Gait recognition holds the promise of robustly identifying subjects based on walking patterns instead of appearance information.
DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protection
In this work, we ask: can diffusion models be used to generate adversarial examples to improve both visual quality and attack performance?
Attribute-Guided Encryption with Facial Texture Masking
In this paper, we propose Attribute Guided Encryption with Facial Texture Masking (AGE-FTM) that performs a dual manifold adversarial attack on FR systems to achieve both good visual quality and high black box attack success rates.
Multi-View Action Recognition Using Contrastive Learning
We present a supervised contrastive learning framework to learn a feature embedding robust to changes in viewpoint, by effectively leveraging multi-view data.
Ranked #14 on
Action Recognition
on NTU RGB+D
Multi-Modal Human Authentication Using Silhouettes, Gait and RGB
In this work, we propose Dual-Modal Ensemble (DME), which combines both RGB and silhouette data to achieve more robust performances for indoor and outdoor whole-body based recognition.
Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses
Under JSTM, we develop novel adversarial attacks and defenses.
Mutual Adversarial Training: Learning together is better than going alone
In other words, we can make a weak model more robust with the help of a strong teacher model.
Segment and Complete: Defending Object Detectors against Adversarial Patch Attacks with Robust Patch Detection
In addition, we design a robust shape completion algorithm, which is guaranteed to remove the entire patch from the images if the outputs of the patch segmenter are within a certain Hamming distance of the ground-truth patch masks.
Identification of Attack-Specific Signatures in Adversarial Examples
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks.
Dual Manifold Adversarial Robustness: Defense against Lp and non-Lp Adversarial Attacks
Using OM-ImageNet, we first show that adversarial training in the latent space of images improves both standard accuracy and robustness to on-manifold attacks.
ATFaceGAN: Single Face Image Restoration and Recognition from Atmospheric Turbulence
To mitigate the degradation due to turbulence which includes deformation and blur, we propose a generative single frame restoration algorithm which disentangles the blur and deformation due to turbulence and reconstructs a restored image.
Subsampled Turbulence Removal Network
Instead of requiring a massive training sample size in deep networks, we purpose a training strategy that is based on a new data augmentation method to model turbulence from a relatively small dataset.
Variational models for joint subsampling and reconstruction of turbulence-degraded images
The energy consists of a fidelity term measuring the discrepancy between the extracted image and the subsampled frames, as well as regularization terms on the extracted image and the subsample.
Image retargeting via Beltrami representation
In this paper, we propose a simple and yet effective method to resize an image, which preserves the geometry of the important content, using the Beltrami representation.
Restoration of Atmospheric Turbulence-distorted Images via RPCA and Quasiconformal Maps
The subsampled image sequence is then stabilized by applying the Robust Principal Component Analysis (RPCA) on the deformation fields between image frames and warping the image frames by a quasiconformal map associated with the low-rank part of the deformation matrix.
