Search Results for author: Simon S. Woo

Found 44 papers, 21 papers with code

Fairness and Robustness in Machine Unlearning

no code implementations18 Apr 2025 Khoa Tran, Simon S. Woo

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.

Fairness Machine Unlearning

Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal

1 code implementation17 Apr 2025 Inzamamul Alam, MD Tanvir Islam, Simon S. Woo

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.

Image Restoration

Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale Dataset

1 code implementation16 Apr 2025 Muhammad Shahid Muneer, Simon S. Woo

Moreover, there is currently no robust multimodal NSFW dataset that includes both prompt and image pairs and adversarial examples.

Adversarial Attack Image Generation

MIXAD: Memory-Induced Explainable Time Series Anomaly Detection

1 code implementation30 Oct 2024 Minha Kim, Kishor Kumar Bhaumik, Amin Ahsan Ali, Simon S. Woo

Addressing this gap, we introduce MIXAD (Memory-Induced Explainable Time Series Anomaly Detection), a model designed for interpretable anomaly detection.

Anomaly Detection Time Series +1

SSMT: Few-Shot Traffic Forecasting with Single Source Meta-Transfer

no code implementations21 Oct 2024 Kishor Kumar Bhaumik, Minha Kim, Fahim Faisal Niloy, Amin Ahsan Ali, Simon S. Woo

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.

Meta-Learning Traffic Prediction +1

LoLI-Street: Benchmarking Low-Light Image Enhancement and Beyond

1 code implementation13 Oct 2024 MD Tanvir Islam, Inzamamul Alam, Simon S. Woo, Saeed Anwar, Ik Hyun Lee, Khan Muhammad

Leveraging the LoLI-Street dataset, we train and evaluate our TriFuse and SOTA models to benchmark on our dataset.

Autonomous Driving Benchmarking +5

UGAD: Universal Generative AI Detector utilizing Frequency Fingerprints

no code implementations12 Sep 2024 Inzamamul Alam, Muhammad Shahid Muneer, Simon S. Woo

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.

Key Detection

GDFlow: Anomaly Detection with NCDE-based Normalizing Flow for Advanced Driver Assistance System

no code implementations9 Sep 2024 KangJun Lee, Minha Kim, Youngho Jun, Simon S. Woo

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.

Anomaly Detection

Blind-Match: Efficient Homomorphic Encryption-Based 1:N Matching for Privacy-Preserving Biometric Identification

1 code implementation12 Aug 2024 Hyunmin Choi, Jiwon Kim, Chiyoung Song, Simon S. Woo, Hyoungshick Kim

We present Blind-Match, a novel biometric identification system that leverages homomorphic encryption (HE) for efficient and privacy-preserving 1:N matching.

Face Recognition Privacy Preserving

Exploring the Impact of Moire Pattern on Deepfake Detectors

no code implementations15 Jul 2024 Razaib Tariq, Shahroz Tariq, Simon S. Woo

Deepfake detection is critical in mitigating the societal threats posed by manipulated videos.

DeepFake Detection Face Swapping

Disrupting Diffusion-based Inpainters with Semantic Digression

no code implementations14 Jul 2024 Geonho Son, Juhun Lee, Simon S. Woo

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.

Misinformation

Impact of Architectural Modifications on Deep Learning Adversarial Robustness

1 code implementation3 May 2024 Firuz Juraev, Mohammed Abuhamad, Simon S. Woo, George K Thiruvathukal, Tamer Abuhmed

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.

Adversarial Robustness Deep Learning

Gradient Alignment for Cross-Domain Face Anti-Spoofing

1 code implementation CVPR 2024 Binh M. Le, Simon S. Woo

Recent advancements in domain generalization (DG) for face anti-spoofing (FAS) have garnered considerable attention.

Domain Generalization Face Anti-Spoofing

Continuous Memory Representation for Anomaly Detection

1 code implementation28 Feb 2024 Joo Chan Lee, Taejune Kim, Eunbyung Park, Simon S. Woo, Jong Hwan Ko

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.

Anomaly Detection

SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Framework

no code implementations9 Jan 2024 Binh M. Le, Jiwon Kim, Simon S. Woo, Kristen Moore, Alsharif Abuadbba, Shahroz Tariq

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.

Benchmarking DeepFake Detection +1

Source-Free Online Domain Adaptive Semantic Segmentation of Satellite Images under Image Degradation

no code implementations4 Jan 2024 Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo

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.

Image Segmentation Online Domain Adaptation +2

Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation

no code implementations28 Dec 2023 Hyunjune Kim, Sangyong Lee, Simon S. Woo

Recently, serious concerns have been raised about the privacy issues related to training datasets in machine learning algorithms when including personal data.

Knowledge Distillation Machine Unlearning

All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models

no code implementations20 Dec 2023 Seunghoo Hong, Juhun Lee, Simon S. Woo

Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets.

All Image Generation

Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning

no code implementations ICCV 2023 Binh M. Le, Simon S. Woo

However, detecting low quality as well as simultaneously detecting different qualities of deepfakes still remains a grave challenge.

DeepFake Detection Face Swapping

Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks

no code implementations21 Jul 2023 Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo, Eric Chan-Tin, Tamer Abuhmed

Deep learning has been rapidly employed in many applications revolutionizing many industries, but it is known to be vulnerable to adversarial attacks.

Deep Learning

HRFNet: High-Resolution Forgery Network for Localizing Satellite Image Manipulation

no code implementations20 Jul 2023 Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo

Existing high-resolution satellite image forgery localization methods rely on patch-based or downsampling-based training.

Image Manipulation Image Segmentation +1

Microbial Genetic Algorithm-based Black-box Attack against Interpretable Deep Learning Systems

no code implementations13 Jul 2023 Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo, Eric Chan-Tin, Tamer Abuhmed

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

no code implementations21 Mar 2023 Binh M. Le, Shahroz Tariq, Simon S. Woo

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.

Adversarial Attack Adversarial Defense +1

Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learning

1 code implementation29 Nov 2022 Eldor Abdukhamidov, Mohammed Abuhamad, Simon S. Woo, Eric Chan-Tin, Tamer Abuhmed

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.

Deep Learning

CFL-Net: Image Forgery Localization Using Contrastive Learning

no code implementations4 Oct 2022 Fahim Faisal Niloy, Kishor Kumar Bhaumik, Simon S. Woo

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.

Contrastive Learning Image Manipulation

Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability

1 code implementation24 Aug 2022 Shahroz Tariq, Binh M. Le, Simon S. Woo

To the best of our understanding, we demonstrate, for the first time, the vulnerabilities of anomaly detection systems against adversarial attacks.

Anomaly Detection Time Series +1

Deepfake Detection for Facial Images with Facemasks

no code implementations23 Feb 2022 Donggeun Ko, Sangjun Lee, Jinyong Park, Saebyeol Shin, Donghee Hong, Simon S. Woo

However, none of the suggested deepfakedetection methods assessed the performance of deepfakes withthe facemask during the pandemic crisis after the outbreak of theCovid-19.

DeepFake Detection Face Swapping +1

KappaFace: Adaptive Additive Angular Margin Loss for Deep Face Recognition

1 code implementation19 Jan 2022 Chingis Oinar, Binh M. Le, Simon S. Woo

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.

Diversity Face Recognition

DA-FDFtNet: Dual Attention Fake Detection Fine-tuning Network to Detect Various AI-Generated Fake Images

no code implementations22 Dec 2021 Young Oh Bang, Simon S. Woo

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.

Few-Shot Learning

Exploring the Asynchronous of the Frequency Spectra of GAN-generated Facial Images

1 code implementation15 Dec 2021 Binh M. Le, Simon S. Woo

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

2 code implementations7 Dec 2021 Binh M. Le, Simon S. Woo

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.

DeepFake Detection Face Swapping +2

Evaluating the Robustness of Time Series Anomaly and Intrusion Detection Methods against Adversarial Attacks

no code implementations29 Sep 2021 Shahroz Tariq, Simon S. Woo

To the best of our knowledge, we are the first to demonstrate the vulnerabilities of anomaly and intrusion detection systems against adversarial attacks.

Intrusion Detection Time Series +1

Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors

no code implementations7 Sep 2021 Hasam Khalid, Minha Kim, Shahroz Tariq, Simon S. Woo

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.

DeepFake Detection Face Swapping

CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation

2 code implementations6 Jul 2021 Minha Kim, Shahroz Tariq, Simon S. Woo

Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments.

Continual Learning Domain Adaptation +3

One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework

1 code implementation1 May 2021 Shahroz Tariq, Sangyup Lee, Simon S. Woo

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.

All Deep Learning +1

Am I a Real or Fake Celebrity? Measuring Commercial Face Recognition Web APIs under Deepfake Impersonation Attack

no code implementations1 Mar 2021 Shahroz Tariq, Sowon Jeon, Simon S. Woo

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.

Face Recognition Face Swapping

T-GD: Transferable GAN-generated Images Detection Framework

1 code implementation ICML 2020 Hyeonseong Jeon, Youngoh Bang, Junyaup Kim, Simon S. Woo

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

2 code implementations5 Jan 2020 Hyeonseong Jeon, Youngoh Bang, Simon S. Woo

Creating fake images and videos such as "Deepfake" has become much easier these days due to the advancement in Generative Adversarial Networks (GANs).

Face Swapping Few-Shot Learning +3

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