Search Results for author:
Found 44 papers, 21 papers with code
Fairness and Robustness in Machine Unlearning
While prior research on approximated unlearning has demonstrated accuracy and efficiency in time complexity, we claim that it falls short of achieving exact unlearning, and we are the first to focus on fairness and robustness in machine unlearning algorithms.
Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal
This paper introduces a novel Saliency-Aware Diffusion Reconstruction (SADRE) framework for watermark elimination on the web, combining adaptive noise injection, region-specific perturbations, and advanced diffusion-based reconstruction.
Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale Dataset
Moreover, there is currently no robust multimodal NSFW dataset that includes both prompt and image pairs and adversarial examples.
MIXAD: Memory-Induced Explainable Time Series Anomaly Detection
Addressing this gap, we introduce MIXAD (Memory-Induced Explainable Time Series Anomaly Detection), a model designed for interpretable anomaly detection.
SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer
Specifically, we use memory-augmented attention to store the heterogeneous spatial knowledge from the source city and selectively recall them for the data-scarce target city.
LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond
Leveraging the LoLI-Street dataset, we train and evaluate our TriFuse and SOTA models to benchmark on our dataset.
Preserving Old Memories in Vivid Detail: Human-Interactive Photo Restoration Framework
Photo restoration technology enables preserving visual memories in photographs.
UGAD: Universal Generative AI Detector utilizing Frequency Fingerprints
In the wake of a fabricated explosion image at the Pentagon, an ability to discern real images from fake counterparts has never been more critical.
GDFlow: Anomaly Detection with NCDE-based Normalizing Flow for Advanced Driver Assistance System
For electric vehicles, the Adaptive Cruise Control (ACC) in Advanced Driver Assistance Systems (ADAS) is designed to assist braking based on driving conditions, road inclines, predefined deceleration strengths, and user braking patterns.
Blind-Match: Efficient Homomorphic Encryption-Based 1:N Matching for Privacy-Preserving Biometric Identification
We present Blind-Match, a novel biometric identification system that leverages homomorphic encryption (HE) for efficient and privacy-preserving 1:N matching.
Exploring the Impact of Moire Pattern on Deepfake Detectors
Deepfake detection is critical in mitigating the societal threats posed by manipulated videos.
Disrupting Diffusion-based Inpainters with Semantic Digression
While their framework suggested a diffusion-friendly approach, the disruption is not sufficiently strong and it requires a significant amount of GPU and time to immunize the context image.
Impact of Architectural Modifications on Deep Learning Adversarial Robustness
By conducting our experiments, we aim to shed light on the critical issue of maintaining the reliability and safety of deep learning models in safety- and security-critical applications.
Gradient Alignment for Cross-Domain Face Anti-Spoofing
Recent advancements in domain generalization (DG) for face anti-spoofing (FAS) have garnered considerable attention.
Continuous Memory Representation for Anomaly Detection
To tackle all of the above challenges, we propose CRAD, a novel anomaly detection method for representing normal features within a "continuous" memory, enabled by transforming spatial features into coordinates and mapping them to continuous grids.
Ranked #33 on
Anomaly Detection
on MVTec AD
SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Framework
Deepfakes have rapidly emerged as a serious threat to society due to their ease of creation and dissemination, triggering the accelerated development of detection technologies.
Source-Free Online Domain Adaptive Semantic Segmentation of Satellite Images under Image Degradation
In this paper, we address source-free and online domain adaptation, i. e., test-time adaptation (TTA), for satellite images, with the focus on mitigating distribution shifts caused by various forms of image degradation.
Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation
Recently, serious concerns have been raised about the privacy issues related to training datasets in machine learning algorithms when including personal data.
All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models
Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets.
Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning
However, detecting low quality as well as simultaneously detecting different qualities of deepfakes still remains a grave challenge.
Ranked #1 on
DeepFake Detection
on FaceForensics++
Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks
Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks.
HRFNet: High-Resolution Forgery Network for Localizing Satellite Image Manipulation
Existing high-resolution satellite image forgery localization methods rely on patch-based or downsampling-based training.
Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems
Our results show that the proposed approach is query-efficient with a high attack success rate that can reach between 95% and 100% and transferability with an average success rate of 69% in the ImageNet and CIFAR datasets.
Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense
Our work is the first carefully analyzes and characterizes these two schools of approaches, both theoretically and empirically, to demonstrate how each approach impacts the robust learning of a classifier.
Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning
We assess the effectiveness of proposed attacks against two deep learning model architectures coupled with four interpretation models that represent different categories of interpretation models.
CFL-Net: Image Forgery Localization Using Contrastive Learning
A key assumption in underlying forged region localization is that there remains a difference of feature distribution between untampered and manipulated regions in each forged image sample, irrespective of the forgery type.
Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability
To the best of our understanding, we demonstrate, for the first time, the vulnerabilities of anomaly detection systems against adversarial attacks.
Deepfake Detection for Facial Images with Facemasks
However, none of the suggested deepfakedetection methods assessed the performance of deepfakes withthe facemask during the pandemic crisis after the outbreak of theCovid-19.
KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition
However, the majority of the proposed methods do not consider the class imbalance issue, which is a major challenge in practice for developing deep face recognition models.
VFP290K: A Large-Scale Benchmark Dataset for Vision-based Fallen Person Detection
Accordingly, detection of these anomalous events is of paramount importance for a number of applications, including but not limited to CCTV surveillance, security, and health care.
Ranked #1 on
Anomaly Detection In Surveillance Videos
on VFP290K
DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images
Our DA-FDFtNet integrates the pre-trained model with Fine-Tune Transformer, MBblockV3, and a channel attention module to improve the performance and robustness across different types of fake images.
Exploring the Asynchronous of the Frequency Spectra of GAN-generated Facial Images
The rapid progression of Generative Adversarial Networks (GANs) has raised a concern of their misuse for malicious purposes, especially in creating fake face images.
ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images
In particular, we propose the Attention-based Deepfake detection Distiller (ADD), which consists of two novel distillations: 1) frequency attention distillation that effectively retrieves the removed high-frequency components in the student network, and 2) multi-view attention distillation that creates multiple attention vectors by slicing the teacher's and student's tensors under different views to transfer the teacher tensor's distribution to the student more efficiently.
Evaluating the Robustness of Time Series Anomaly and Intrusion Detection Methods against Adversarial Attacks
To the best of our knowledge, we are the first to demonstrate the vulnerabilities of anomaly and intrusion detection systems against adversarial attacks.
Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors
On the other hand, to develop a good deepfake detector that can cope with the recent advancements in deepfake generation, we need to have a detector that can detect deepfakes of multiple modalities, i. e., videos and audios.
FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset
We generate this dataset using the most popular deepfake generation methods.
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation
Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments.
FReTAL: Generalizing Deepfake Detection using Knowledge Distillation and Representation Learning
We use FReTAL to perform domain adaptation tasks on new deepfake datasets while minimizing catastrophic forgetting.
TAR: Generalized Forensic Framework to Detect Deepfakes using Weakly Supervised Learning
This motivates us to develop a generalized model to detect different types of deepfakes.
One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework
Beyond detecting a single type of DF from benchmark deepfake datasets, we focus on developing a generalized approach to detect multiple types of DFs, including deepfakes from unknown generation methods such as DeepFake-in-the-Wild (DFW) videos.
Am I a Real or Fake Celebrity? Measuring Commercial Face Recognition Web APIs under Deepfake Impersonation Attack
Moreover, we propose practical defense strategies to mitigate DI attacks, reducing the attack success rates to as low as 0% and 0. 02% for targeted and non-targeted attacks, respectively.
A Convolutional LSTM based Residual Network for Deepfake Video Detection
Also, they do not take advantage of the temporal information of the video.
T-GD: Transferable GAN-generated Images Detection Framework
First, we train the teacher model on the source dataset and use it as a starting point for learning the target dataset.
FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network
Creating fake images and videos such as "Deepfake" has become much easier these days due to the advancement in Generative Adversarial Networks (GANs).
