no code implementations • 18 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.
1 code implementation • 17 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.
1 code implementation • 16 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.
1 code implementation • 30 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.
no code implementations • 21 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.
1 code implementation • 13 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.
no code implementations • 12 Oct 2024 • Seung-Yeon Back, Geonho Son, Dahye Jeong, Eunil Park, Simon S. Woo
Photo restoration technology enables preserving visual memories in photographs.
no code implementations • 12 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.
no code implementations • 9 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.
1 code implementation • 12 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.
no code implementations • 15 Jul 2024 • Razaib Tariq, Shahroz Tariq, Simon S. Woo
Deepfake detection is critical in mitigating the societal threats posed by manipulated videos.
no code implementations • 14 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.
1 code implementation • 3 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.
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.
1 code implementation • 28 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.
Ranked #33 on
Anomaly Detection
on MVTec AD
no code implementations • 9 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.
no code implementations • 4 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.
no code implementations • 28 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.
no code implementations • 20 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.
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.
Ranked #1 on
DeepFake Detection
on FaceForensics++
no code implementations • 21 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.
no code implementations • 20 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.
no code implementations • 13 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.
no code implementations • 21 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.
1 code implementation • 29 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.
no code implementations • 4 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.
1 code implementation • 24 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.
no code implementations • 23 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.
1 code implementation • 19 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.
1 code implementation • NeurIPS 2021 Track Datasets and Benchmarks 2022 • Jaeju An, Jeongho Kim, Hanbeen Lee, Jinbeom Kim, Junhyung Kang, Saebyeol Shin, Minha Kim, Donghee Hong, Simon S. Woo
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
no code implementations • 22 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.
1 code implementation • 15 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.
2 code implementations • 7 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.
no code implementations • 29 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.
no code implementations • 7 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.
1 code implementation • 11 Aug 2021 • Hasam Khalid, Shahroz Tariq, Minha Kim, Simon S. Woo
We generate this dataset using the most popular deepfake generation methods.
2 code implementations • 6 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.
no code implementations • 28 May 2021 • Minha Kim, Shahroz Tariq, Simon S. Woo
We use FReTAL to perform domain adaptation tasks on new deepfake datasets while minimizing catastrophic forgetting.
1 code implementation • 13 May 2021 • Sangyup Lee, Shahroz Tariq, Junyaup Kim, Simon S. Woo
This motivates us to develop a generalized model to detect different types of deepfakes.
1 code implementation • 1 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.
no code implementations • 1 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.
1 code implementation • 16 Sep 2020 • Shahroz Tariq, Sangyup Lee, Simon S. Woo
Also, they do not take advantage of the temporal information of the video.
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.
2 code implementations • 5 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).