-
- [Research] Three Short Papers accepted at TheWebConf (WWW) 2025 from Professor Simon S. Woo’s Lab (DASH Lab)
- The Data-driven AI & Security HCI Lab (DASH Lab, Advisor: Simon S. Woo) has had three short papers accepted for publication at the International World Wide Web Conference (WWW), a top-tier international conference in BK Computer Science, covering web technologies, internet advancements, data science, and artificial intelligence. The papers will be presented in April in Sydney, Australia. 1. Towards Safe Synthetic Image Generation On the Web: A Multimodal Robust NSFW Defense and Million Scale Dataset, WWW 2025 Authors:Muhammad Shahid Muneer (Ph.D. Student, Department of Software), Simon S. Woo (Professor, Department of Software, Sungkyunkwan University) 2. Fairness and Robustness in Machine Unlearning, WWW 2025 Authors: Khoa Tran (Integrated M.S./Ph.D. Student, Department of Software), Simon S. Woo (Professor, Department of Software, Sungkyunkwan University) Machine unlearning addresses the challenge of removing the influence of specific data from a pretrained model, which is a crucial issue in privacy protection. While existing approximated unlearning techniques emphasize accuracy and time efficiency, they fail to achieve exact unlearning. In this study, we are the first to incorporate fairness and robustness into machine unlearning research. Our study analyzes the relationship between fairness and robustness based on fairness conjectures, and experimental results confirm that a larger fairness gap makes the model more vulnerable. Additionally, we demonstrate that state-of-the-art approximated unlearning methods are highly susceptible to adversarial attacks, significantly degrading model performance. Therefore, we argue that fairness-gap measurement and robustness metrics should be essential evaluation criteria for unlearning algorithms. Finally, our findings show that unlearning at the intermediate and final layers is sufficient while also improving time and memory efficiency. 3. SADRE: Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal, WWW 2025 Authors: Inzamamul Alam (Ph.D. Student, Department of Software), Simon S. Woo (Professor, Department of Software, Sungkyunkwan University) To address the robustness limitations of existing watermarking techniques, this study proposes SADRE (Saliency-Aware Diffusion Reconstruction), a novel watermark removal framework. SADRE applies saliency mask-guided noise injection and diffusion-based reconstruction to preserve essential image features while effectively removing watermarks. Additionally, it adapts to varying watermark strengths through adaptive noise adjustment and ensures high-quality image restoration via a reverse diffusion process. Experimental results demonstrate that SADRE outperforms state-of-the-art watermarking techniques across key performance metrics, including PSNR, SSIM, Wasserstein Distance, and Bit Recovery Accuracy. This research establishes a theoretically robust and practically effective watermark removal solution, proving its reliability for real-world web content applications.
-
- 작성일 2025-03-04
- 조회수 140
-
- [Research] One paper accepted at EuroS&P 2025 from Professor Simon S Woo's (DASH Lab)
- The Data-driven AI & Security HCI Lab (DASH Lab, Advisor: Simon S. Woo) has had one System of Knowledge (SoK) paper accepted for publication at the 10th IEEE European Symposium on Security and Privacy (Euro S&P), a prestigious international conference covers Machine Learning Security, System & Network Security, Cryptographic Protocols, Data Privacy. The papers will be presented in July in Venice, Italy. SoK: Systematization and Benchmarking of Deepfake Detectors in a Unified Framework, EuroS&P 2025 Authors: Binh Le and Jiwon Kim (Ph.D. Student, Department of Software), Simon S. Woo (Professor, Department of Software, Sungkyunkwan University) This work is jointly performed with CSIRO Data61 as an international collaboration. Paper Link: https://arxiv.org/abs/2401.04364
-
- 작성일 2025-03-01
- 조회수 118
-
-
- [Research] [Prof. Hyoungshick Kim] secLab, Wins Top Prize in Financial Security Institute
- [Prof. Hyoungshick Kim] secLab, Wins Top Prize in Financial Security Institute ▲ (From left) Researcher Sang-Yoon Seok, President Chul-Woong Kim of the Financial Security Agency, Graduate Student Hyunmin Choi, and Student Jihoon Kim Jihoon Kim and Hyunmin Choi, members of the Security Engineering Lab (supervised by Professor Hyungshick Kim) in the Department of Electrical, Electronic, and Computer Engineering, collaborated with Sang-Yoon Seok, a researcher at Naver Cloud, to win the top prize at the 8th Financial Security Institute’s Paper Contest. The award ceremony was held on Thursday, November 7, at the Conrad Hotel in Yeouido, Seoul. Hyunmin Choi is currently conducting research on privacy protection at Naver Cloud. The annual paper competition, hosted by the Financial Security Institute, invites submissions on topics such as changes in the financial environment, new technologies, and improvements to laws and regulations. Eight outstanding papers are selected each year, and winners receive preferential benefits when applying to the Financial Security Institute. Hyunmin Choi, the corresponding author and a doctoral candidate in the Department of Computer Science and Engineering, stated, “With the mandatory use of financial MyData APIs, the importance of data privacy technology is increasing. Our paper focused on enhancing security through homomorphic encryption and enabling data combination technologies.” Jihoon Kim, the first author and an undergraduate student in the Department of Mathematics, shared, “This research was a valuable learning experience, and I hope to continue contributing to advancements in security technology.” Professor Hyungshick Kim added, “This project provided students with a meaningful opportunity to apply the latest security technologies in real-world settings through collaboration with Naver Cloud.”
-
- 작성일 2024-11-21
- 조회수 531
-
- [Research] [Prof. Sooyoung Cha] SALab, Papers Approved for Publication at the ICSE 2025 International Conference
- [Prof. Sooyoung Cha] SALab, Papers Approved for Publication at the ICSE 2025 International Conference ■ Title: TopSeed: Learning Seed Selection Strategies for Symbolic Execution from Scratch ■ Author of a paper: Jaehyeok Lee, Prof. Sooyoung Cha ■ Conference: IEEE/ACM International Conference on Software Engineering (ICSE 2025) ■ Abstract: We present TopSeed, a new approach that automatically selects optimal seeds to enhance symbolic execution. Recently, the performance of symbolic execution has significantly improved through various state-of-the-art techniques, including search strategies and state-pruning heuristics. However, these techniques have typically demonstrated their effectiveness without considering “seeding”, which efficiently initializes program states for exploration. This paper aims to select valuable seeds from candidate inputs generated during interactions with any symbolic execution technique, without the need for a predefined seed corpus, thereby maximizing the technique's effectiveness. One major challenge is the vast number of candidates, making it difficult to identify promising seeds. To address this, we introduce a customized online learning algorithm that iteratively groups candidate inputs, ranks each group, and selects a seed from the top-ranked group based on data accumulated during symbolic execution. Experimental results on 17 open-source C programs show that TopSeed significantly enhances four distinct cutting-edge techniques, implemented on top of two symbolic executors, in terms of branch coverage and bug-finding abilities.
-
- 작성일 2024-11-04
- 조회수 628
-
- [Research] [prof.Simon S. Woo] DASH Lab, Two Papers Approved for Publication at the CIKM 2024 International Conference
- [prof.Simon S. Woo] DASH Lab, Two Papers Approved for Publication at the CIKM 2024 International Conference 1. IDENTIFY: Integral Radial and Spatial Fourier Analysis for AI-Generated Image Authentication (full paper) Writer: Inzamamul Alam, Muhammad Shahid Muneer, and Prof. Simon S. Woo This study proposes a method for detecting deepfakes generated by a new generative AI (Diffusion) technique using Integral Radial and Spatial Fourier Analysis with high performance. Notably, the proposed method shows 12-28% higher performance compared to existing approaches. IDENTIFY: Integral Radial and Spatial Fourier Analysis for AI-Generated Image Authentication, Inzamamul Alam, Muhammad Shahid Muneer, and Simon S. Woo*, 33rd ACM International Conference on Information & Knowledge Management (CIKM), Boise, Idaho, USA, October 2024 2. Deep Journey Hierarchical Attention Networks for Conversion Predictions in Digital Marketing (full paper) Writer: Girim Ban, Hyeonseok Yun, Banseok Lee, David Sung, and Prof. Simon S. Woo This study proposes Deep Journey Hierarchical Attention Networks (DJHAN) to enhance user conversion prediction in digital marketing, improving key metrics such as Conversion Rate (CVR) and Return on Ad Spend (ROAS) compared to existing methods. The proposed model demonstrated high performance when applied to real marketing data from KT/NasMedia. Deep Journey Hierarchical Attention Networks for Predictions in Digital Marketing Girim Ban, Hyeonseok Yun, Banseok Lee, David Sung, and Simon S. Woo* 33rd ACM International Conference on Information & Knowledge Management (CIKM), Boise, Idaho, USA, October 2024
-
- 작성일 2024-08-29
- 조회수 957
-
- Papers from Prof. Jinkyu Lee’s Lab. (RTCL@SKKU) published in ACM/IEEE DAC 2024 and IEEE RTAS 2024
- A paper from RTCL@SKKU (Advisor: Jinkyu Lee) has been published in ACM/IEEE DAC 2024 and IEEE RTAS 2024. ACM/IEEE DAC 2024 Website https://www.dac.com/ IEEE RTAS 2024 Website https://2024.rtas.org/ Real-Time Computing Lab. Website https://rtclskku.github.io/website/ - Paper Title: RT-MDM: Real-Time Scheduling Framework for Multi-DNN on MCU Using External Memory - Abstract: As the application scope of DNNs executed on microcontroller units (MCUs) extends to time-critical systems, it becomes important to ensure timing guarantees for increasing demand of DNN inferences. To this end, this paper proposes RT-MDM, the first Real-Time scheduling framework for Multiple DNN tasks executed on an MCU using external memory. Identifying execution-order dependencies among segmented DNN models and memory requirements for parallel execution subject to the dependencies, we propose (i) a segment-group-based memory management policy that achieves isolated memory usage within a segment group and sharded memory usage across different segment groups, and (ii) an intra-task scheduler specialized for the proposed policy. Implementing RT-MDM on an actual system and optimizing its parameters for DNN segmentation and segment-group mapping, we demonstrate the effectiveness of RT-MDM in accommodating more DNN tasks while providing their timing guarantees. - Paper Title: RT-Swap: Addressing GPU Memory Bottlenecks for Real-Time Multi-DNN Inference - Abstract: The increasing complexity and memory demands of Deep Neural Networks (DNNs) for real-time systems pose new significant challenges, one of which is the GPU memory capacity bottleneck, where the limited physical memory inside GPUs impedes the deployment of sophisticated DNN models. This paper presents, to the best of our knowledge, the first study of addressing the GPU memory bottleneck issues, while simultaneously ensuring the timely inference of multiple DNN tasks. We propose RT-Swap, a real-time memory management framework, that enables transparent and efficient swap scheduling of memory objects, employing the relatively larger CPU memory to extend the available GPU memory capacity, without compromising timing guarantees. We have implemented RT-Swap on top of representative machine-learning frameworks, demonstrating its effectiveness in making significantly more DNN task sets schedulable at least 72% over existing approaches even when the task sets demand up to 96.2% more memory than the GPU’s physical capacity. Jinkyu Lee | jinkyu.lee@skku.edu | RTCL@SKKU | https://rtclskku.github.io/website/
-
- 작성일 2024-06-28
- 조회수 732
-
- [Research] DASH Lab won the Best Paper Running-Up Award (2nd Best Paper) at PAKDD 2024 in Taiwan
- Binh M. Le and Simon S. Woo’s paper, “SEE: Spherical Embedding Expansion for Improving Deep Metric Learning,” received the the Best Paper Running-Up Award (2nd best paper) in PAKDD 2024 (BK CS IF=1), held in Taipei in May 2024. Here is the background information about the award: “This year, PAKDD received 720 excellent submissions, and the selection process was competitive, rigorous, and thorough with over 500 PC and 100 SPC members. An award committee was formed by a chair and four committee members from different countries. There are only one Best Paper Award, two Best Paper Running-Up Awards, and one Best Student Paper Award.” Paper Link: https://link.springer.com/chapter/10.1007/978-981-97-2253-2_11 https://pakdd2024.org/award24awardpakdd24/
-
- 작성일 2024-06-07
- 조회수 1193
-
- [Prof. Woo, Simon Sungil] DASH Lab, Approval for AAAI 2024 publication
- [Prof. Woo, Simon Sungil] DASH Lab, Approval for AAAI 2024 publication [ Paper #1 ] ※ Paper Title: All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models ※ paper link: https://doi.org/10.48550/arXiv.2312.12807 Seunghoo Hong†, Juhun Lee†, and Simon S. Woo*, “All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models”, Proceedings of the 38th annual AAAI Conference on Artificial Intelligence (AAAI), 2024. Abstract: Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content, which allows the model to directly generate them. Given that retraining these large models on individual concept deletion requests is infeasible, fine-tuning algorithms have been developed to tackle concept erasing in diffusion models. While these algorithms yield good concept erasure, they all present one of the following issues: 1) the corrupted feature space yields synthesis of disintegrated objects, 2) the initially synthesized content undergoes a divergence in both spatial structure and semantics in the generated images, and 3) sub-optimal training updates heighten the model's susceptibility to utility harm. These issues severely degrade the original utility of generative models. In this work, we present a new approach that solves all of these challenges. We take inspiration from the concept of classifier guidance and propose a surgical update on the classifier guidance term while constraining the drift of the unconditional score term. Furthermore, our algorithm empowers the user to select an alternative to the erasing concept, allowing for more controllability. Our experimental results show that our algorithm not only erases the target concept effectively but also preserves the model’s generation capability. [ Paper #2 ] ※ Paper Title: Layer Attack Unlearning: Fast and Accurate Machine Unlearning viaLayer Level Attack and Knowledge Distillation ※ paper link: https://arxiv.org/pdf/2312.16823.pdf Hyunjune Kim, Sangyong Lee, and Simon S. Woo*, “Layer Attack Unlearning: Fast and Accurate Machine Unlearning via Layer Level Attack and Knowledge Distillation”, Proceedings of the 38th annual AAAI Conference on Artificial Intelligence (AAAI), 2024. Abstract: Recently, serious concerns have been raised about the privacy issues related to training datasets in machine learning algorithms when including personal data. Various regulations in different countries, including the GDPR, grant individuals to have personal data erased, known as ‘the right to be forgotten’ or ‘the right to erasure’. However, there has been less research on effectively and practically deleting the requested personal data from the training set while not jeopardizing the overall machine learning performance. In this work, we propose a fast and novel machine unlearning paradigm at the layer level called layer attack unlearning, which is highly accurate and fast compared to existing machine unlearning algorithms. We introduce the Partial-PGD algorithm to locate the samples to forget efficiently. In addition, we only use the last layer of the model inspired by the Forward-Forward algorithm for unlearning process. Lastly, we use Knowledge Distillation (KD) to reliably learn the decision boundaries from the teacher using soft label information to improve accuracy performance. We conducted extensive experiments with SOTA machine unlearning models and demonstrated the effectiveness of our approach for accuracy and end-to-end unlearning performance.
-
- 작성일 2024-01-30
- 조회수 1246
-
- [Prof. Koo,Hyung joon] SecAILab, Approval for A SIACCS 2024 publication
- [Prof. Koo,Hyung joon] SecAILab, Approval for ACM Asia Conference on Computer and Communications Security, 2024 (ASIACCS ’24) publication "BinAdapter: Leveraging Continual Learning for Inferring Function Symbol Names in a Binary" Abstract. Binary reverse engineering is crucial to gain insights into the inner workings of a stripped binary. Yet, it is challenging to read the original semantics from a binary code snippet because of the unavailability of high-level information in the source, such as function names, variable names, and types. Recent advancements in deep learning show the possibility of recovering such vanished information with a well-trained model from a pre-defined dataset. Albeit a static model’s notable performance, it can hardly cope with an ever-increasing data stream (e.g., compiled binaries) by nature. The two viable approaches for ceaseless learning are retraining the whole dataset from scratch and fine-tuning a pre-trained model; however, retraining suffers from large computational overheads and fine-tuning from performance degradation (i.e., catastrophic forgetting). Lately, continual learning (CL) tackles the problem of handling incremental data in security domains (e.g., network intrusion detection, malware detection) using reasonable resources while maintaining performance in practice. In this paper, we focus on how CL assists the improvement of a generative model that predicts a function symbol name from a series of machine instructions. To this end, we introduce BinAdapter, a system that can infer function names from an incremental dataset without performance degradation from an original dataset by leveraging CL techniques. Our major finding shows that incremental tokens in the source (i.e., machine instructions) or the target (i.e., function names) largely affect the overall performance of a CL-enabled model. Accordingly, BinAdapter adopts three built-in approaches: i) inserting adapters in case of no incremental tokens in both the source and target, ii) harnessing multilingual neural machine translation (M-NMT) and fine-tuning the source embeddings with i) in case of incremental tokens in the source, and iii) fine-tuning target embeddings with ii) in case of incremental tokens in both. To demonstrate the effectiveness of BinAdapter, we evaluate the above three scenarios using incremental datasets with or without a set of new tokens (e.g., unseen machine instructions or function names), spanning across different architectures and optimization levels. Our empirical results show that BinAdapter outperforms the state-of-the-art CL techniques for an F1 of up to 24.3% or a Rouge-l of 21.5% in performance.
-
- 작성일 2024-01-26
- 조회수 739