대학소식 게시판목록 | Sungkyunkwan University ( SKKU ) College of Computing and Informatics

본문 바로가기
주메뉴 바로가기
서브메뉴 바로가기

Campus Life

Campus Life
- About Us
- Undergraduate
- Graduate
- Professors
- Research
- Student
- Campus Life
News

Campus Life

News

[Research] One paper accepted at ACL 2026 from Professor young Joong Ko's NLP Lab NEW

자연어처리연구실(NLP lab, 지도교수: 고영중)의 논문 1편이 인공지능 및 자연어처리 분야의 Top-tier 국제학술대회인 ACL 2026 (The 64th Annual Meeting of the Association for Computational Linguistics)의 Findings에 게재되었습니다. 논문: ConvX: A Lightweight Converter to Bridge Indexed Dense Representations and Large Language Models for Retrieval-Augmented Generation (인공지능학과 박사과정 최봉근, 인공지능학과 박사과정 김근하, 인공지능학과 석박사통합과정 한준호) 논문 요약: 본 연구에서는 RAG 파이프라인의 치명적인 효율성 문제와, 이를 해결하기 위한 기존 압축 기반 방법론들이 검색된 문맥을 다시 인코딩하며 발생하는 이중 인코딩(double-encoding) 문제를 해소하기 위해, 검색기가 생성한 색인된 밀집 표현(dense representation)을 직접 활용하여 긴 텍스트 문맥을 전적으로 대체하는 효과적인 압축 기반 RAG 프레임워크인 ConvX를 제안합니다. 제안한 방법은 경량 변환기(converter)를 통해 단일 밀집 표현을 고정된 수의 메모리 슬롯으로 확장합니다. 메모리 슬롯으로부터 문단 수준의 어휘 정보를 복원하도록 변환기를 학습합니다. 변환기를 통해 생성된 메모리 슬롯은 LLM의 기존 토큰 임베딩과 특성이 상이하므로, LLM이 메모리 슬롯에 대한 내용을 복원할 수 있도록 사전학습을 수행합니다. 이때, 다중 문서의 RAG 시스템에 적용할 수 있도록 단일 및 다중 문단 메모리 슬롯을 복원하도록 학습합니다. 이러한 설계는 입력 길이와 계산 오버헤드를 크게 줄이면서도 효율적인 지식 통합을 가능하게 합니다. 실험 결과, 제안한 모델은 RAG 환경에서 기존의 ad-hoc 문맥 압축 기법들 대비 우수한 성능을 달성하는 동시에, 추론 효율성을 크게 향상시킴을 확인하였습니다. Abstract: Retrieval-Augmented Generation (RAG) has significantly advanced open-domain question answering and dialogue systems by incorporating external knowledge into large language models. Despite its effectiveness, existing RAG pipelines suffer from critical efficiency limitations. In particular, modern transformer-based generators exhibit quadratic or higher computational complexity with respect to input sequence length and hidden dimensionality, leading to substantial inference latency as model scales and contextual inputs increase. This issue is exacerbated in RAG settings, where retrieved contexts substantially expand the input prompt. To alleviate this challenge, we propose an effective compression-based RAG framework, ConvX, that directly leverages indexed dense representations produced by a retriever, entirely substituting to long text contexts. Our approach expands a single dense representation into a fixed number of memory slots using a lightweight converter to provide rich lexical information. This design enables efficient knowledge integration while significantly reducing input length and computational overhead. Empirical evaluations demonstrate that the proposed model achieves outstanding performances compared to existing ad-hoc context compression methods in RAG setting, while offering substantially improved inference efficiency. 고영중 교수: yjko@skku.edu, nlp.skku.edu, 자연어처리연구실: nlplab.skku.edu
- 작성일 2026-06-08
- 조회수 68
[Research] One paper accepted at ACM KDD 2026 from Professor Tamer’s InfoLab

Professor Tamer’s InfoLab has had a paper accepted for presentation at ACM KDD 2026, a premier international conference in data science, AI, knowledge discovery, and data mining, to be held from August 9–13, 2026, in Jeju, South Korea. Figure 1 Example advantages of VisionDES over static ensemble models. Models with red highlights are attacked models. The accepted paper, titled “VisionDES: Robust and Explainable Dynamic Vision Ensemble,” introduces the first dynamic ensemble selection framework for vision tasks. VisionDES uses deep vision embeddings and approximate nearest-neighbor search to identify a local region of competence for each test image, then dynamically selects and weights the most reliable models for the final predictions. The method is designed to improve robustness under adversarial attacks and distribution shifts while providing novel instance-level interpretability. Figure 2 Framework of the proposed VisionDES, consisting of three main stages: training, selection, and aggregation. The paper reports extensive evaluations on several image datasets under clean conditions, adversarial attacks, and distribution shifts. VisionDES outperforms static ensembles and uncertainty-based dynamic ensemble methods, achieving up to 20% higher robust accuracy under strong attacks and 2–3% higher accuracy under distribution shifts. Figure 3 Interpretability for test images under benign (top) and adversarial (bottom) conditions. We show each model’s behavior in the Region of Competence (RoC), predictions, and RoC samples with their L2 distances (computed via FAISS). VisionDES strengthens trustworthy computer vision by making ensemble models more adaptive, more robust to adversarial attacks and distribution shifts, and more explainable at the level of individual predictions. For more details about InfoLab research activities, visit https://infolab.skku.edu
- 작성일 2026-05-22
- 조회수 434
[Research] Security Engineering Laboratory (SecLab) under Professor Kim Hyung-sik – Paper Accepted for Publication at the S&P 2025

Security Engineering Laboratory (SecLab) at SKKU (Advisor: Kim Hyung-sik, https://seclab.skku.edu) – "Open Sesame! On the Security and Memorability of Verbal Passwords" Accepted for IEEE Symposium on Security and Privacy (S&P) 2025 The paper "Open Sesame! On the Security and Memorability of Verbal Passwords," conducted by Ph.D. candidate Kim Eun-soo and Professor Kim Hyung-sik at the Security Engineering Laboratory, has been accepted for publication at the IEEE Symposium on Security and Privacy (S&P) 2025, one of the most prestigious conferences in the field of computer security. The study was conducted in collaboration with Professor Kim Doo-won of the University of Tennessee and alumnus Lee Ki-ho from the Security Engineering Laboratory (currently at ETRI). The research quantitatively analyzed the security and memorability of verbal passwords through two large-scale user experiments, demonstrating that verbal passwords offer a practical and secure alternative to traditional text-based passwords by overcoming their inherent limitations. In the first user experiment, verbal passwords freely generated by 2,085 participants were evaluated for both short-term and long-term memorability as well as security. Security testing conducted using the PassphraseGPT model—trained on over 20 million common English phrases—revealed that approximately 39.76% of the user-generated verbal passwords could be predicted within one billion guess attempts. In the second experiment, involving 600 participants, a password creation policy that enforced a minimum word count and incorporated a blocklist was implemented. This approach significantly improved security while maintaining ease of memorability. In long-term memory tests, 65.6% of users in the verbal password group were able to successfully recall their passwords, compared to 54.11% for text-based passwords. Moreover, the proportion of verbal passwords susceptible to guessing attacks was lower than that of text passwords, indicating a stronger resistance to such attacks. This research has been highly acclaimed for demonstrating that verbal passwords provide a practical and secure alternative to text-based passwords in scenarios where keyboard input is either impossible or inconvenient—such as with smart assistants, wearable devices, in-vehicle systems, and VR/AR environments. The study will be presented in May 2025 in San Francisco, California, USA. Abstract Despite extensive research on text passwords, the security and memorability of verbal passwords—spoken rather than typed—remain underexplored. Verbal passwords hold significant potential for scenarios where keyboard input is impractical (e.g., smart speakers, wearables, vehicles) or users have motor impairments that make typing difficult. Through two large-scale user studies, we assessed the viability of verbal passwords. In our first study (N = 2,085), freely chosen verbal passwords were found to have a limited guessing space, with 39.76% cracked within 10^9 guesses. However, in our second study (n = 600), applying word count and blocklist policies for verbal password creation significantly enhanced verbal password performance, achieving better memorability and security than traditional text passwords. Specifically, 65.6% of verbal password users (under the password creation policy using minimum word counts and a blocklist) successfully recalled their passwords in long-term tests, compared to 54.11% for text passwords. Additionally, verbal passwords with enforced policies exhibited a lower crack rate (6.5%) than text passwords (10.3%). These findings highlight verbal passwords as a practical and secure alternative for contexts where text passwords are infeasible, offering strong memorability with robust resistance to guessing attacks.
- 작성일 2025-04-29
- 조회수 7677
[Research] Security Engineering Laboratory (Advisor: Kim Hyung-sik) – Two Papers Accepted for Oral Sessions at The Web Conference

The Security Engineering Laboratory, under the supervision of Professor Kim Hyung-sik, in collaboration with Professor Kim Doo-won from the University of Tennessee, has had two research papers accepted for oral sessions at The Web Conference (WWW) 2025, one of the premier international conferences in the web domain. In this research, alumnus Lee Ki-ho, a former member of the Security Engineering Laboratory (currently at ETRI), participated as a visiting researcher at the University of Tennessee and collaborated with Professor Kim Hyung-sik. Both papers, based on extensive empirical data, quantitatively analyze the characteristics and structures of phishing attacks. They have been highly acclaimed for providing a fundamental understanding of phishing attacks and proposing new countermeasures. The presentations are scheduled to take place in May 2025 in Sydney, Australia. Paper 1. 7 Days Later: Analyzing Phishing-Site Lifespan After DetectedThis paper presents an empirical study analyzing the lifetime and evolution of phishing sites after detection. Over a period of five months, 286,237 phishing URLs were tracked at 30-minute intervals to examine the attack patterns of phishing sites, shedding light on why the effectiveness of conventional phishing detection strategies is diminishing. Phishing sites have a short lifespan—with an average survival time of 54 hours and a median of 5.46 hours—highlighting the limitations of training and detection approaches. For instance, Google Safe Browsing detects phishing sites, on average, 4.5 days after their emergence; however, 84% of phishing sites cease operations before detection, demonstrating the inherent limitations of such detection methods. Paper 2. What's in Phishers: A Longitudinal Study of Security Configurations in Phishing Websites and Kits This paper presents a systematic analysis of phishing infrastructure by comprehensively examining the security configurations and structural vulnerabilities based on a combined dataset of 906,731 phishing websites and 13,344 phishing kits collected over a period of 2 years and 7 months. The study has attracted attention for proposing a proactive strategy that leverages the structural weaknesses of phishing sites to neutralize the attack infrastructure, thereby moving away from traditional passive detection and blocking methods and towards an early shutdown approach for phishing sites.
- 작성일 2025-04-29
- 조회수 7765
[Research] IEEE S&P 2025 Paper Acceptance Announcement from Professor Lee Ho-jun’s Research Laboratory (SSLab)

[IEEE S&P 2025 Acceptance Announcement – SSLab, Professor Hojoon Lee] The paper from the System Security Laboratory (SSLab), under the supervision of Professor Hojoon Lee, has been accepted for publication at IEEE S&P 2025, one of the four premier international conferences in the security field. The paper is scheduled for presentation in May in San Francisco, California, USA. Title: IncognitOS: A Practical Unikernel Design for Full-System Obfuscation in Confidential Virtual Machines Authors: Kha Dinh Duy, Jaeyoon Kim, Hajeong Lim, Hojoon Lee Summary: Recent works have repeatedly proven the practicality of side-channel attacks in undermining the confidentiality guarantees of Trusted Execution Environments such as Intel SGX. Meanwhile, the trusted execution in the cloud is witnessing a trend shift towards confidential virtual machines (CVMs). Unfortunately, several side-channel attacks have survived the shift and are feasible even for CVMs, along with the new attacks discovered on the CVM architectures. Previous works have explored defensive measures for securing userspace enclaves (i.e., Intel SGX) against side-channel attacks. However, the design space for a CVM-based obfuscation execution engine is largely unexplored. This paper proposes a unikernel design named IncognitOS to provide full-system obfuscation for CVM-based cloud workloads. IncognitOS fully embraces unikernel principles such as minimized TCB and direct hardware access to render full-system obfuscation feasible. IncognitOS retrofits two key OS components, the scheduler and memory management, to implement a novel adaptive obfuscation scheme. IncognitOS's scheduling is designed to be self-sovereign from the timer interrupts from the untrusted hypervisor with its synchronous tick delivery. This allows IncognitOS to reliably monitor the frequency of the hypervisor's possession of execution control (i.e., VMExits) and adjust the frequency of memory rerandomization performed by the paging subsystem, which transparently performs memory rerandomization through direct MMU access. The resulting IncognitOS design makes a case for self-obfuscating unikernel as a secure CVM deployment strategy while further advancing the obfuscation technique compared to previous works. Evaluation results demonstrate IncognitOS's resilience against CVM attacks and show that its adaptive obfuscation scheme enables practical performance for real-world programs.
- 작성일 2025-04-29
- 조회수 7670
[Faculty] Professor Hong Joo-hwa Appears on SBS Program

Professor Hong Joo-hwa Appears on SBS Program URL: https://programs.sbs.co.kr/culture/unansweredquestions/clip/55073/22000592156
- 작성일 2025-04-16
- 조회수 1892
[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 2025-03-05
- 조회수 6563
[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 2025-03-05
- 조회수 6432
[Research] Professor Woo Hongwook’s Research Lab (CSI Lab), ICLR 2025 Paper Acceptance

[Professor Woo Hongwook’s Research Lab (CSI Lab), ICLR 2025 Paper Acceptance] Two papers from CSI Lab (Supervised by Professor Woo Hongwook) have been accepted for presentation at ICLR 2025 (The 13th International Conference on Learning Representations), a prestigious conference in the field of Artificial Intelligence. The papers will be presented in April 2025 at the Singapore Expo in Singapore. 1. Paper “Model Risk-sensitive Offline Reinforcement Learning” The author of this paper is Kwangpyo Yoo, a Ph.D. candidate in the Department of Software. This study proposes a Model Risk-sensitive Reinforcement Learning (Model Risk-sensitive RL) framework for critical mission domains, such as robotics and finance, where decision-making is crucial. The paper particularly details a model risk-sensitive offline reinforcement learning technique (MR-IQN). MR-IQN aims to minimize the "model risk" loss in cases where the model's learned data differs from the real environment, leading to decreased accuracy. To achieve this, it calculates the model's confidence in each data point and evaluates the model risk per data point using a Critic-Ensemble Criterion. It also introduces a Fourier Feature Network that limits the gap between the actual policy's value function and the inferred policy’s value in an offline setting. MR-IQN outperformed other state-of-the-art risk-sensitive reinforcement learning techniques in experiments conducted in MT-Sim (financial trading environment) and AirSim (autonomous driving simulator), achieving lower risk and higher average performance. 2. Paper “NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains” This paper was co-authored by Wonje Choi (Ph.D. candidate, Department of Software), Jinwoo Park (Master’s student, Department of Artificial Intelligence), Sanghyun Ahn (Master’s student, Department of Software), and Daehui Lee (Integrated Master’s and Ph.D. candidate). The study proposes a Neuro-symbolic Continual Learner (NeSyC) framework that continuously generalizes knowledge (Actionable Knowledge) from embodied experiences to be applied to various tasks in open-domain physical environments. NeSyC mimics the human cognitive process of hypothesizing and deducing (hypothetico-deductive reasoning) to improve performance in open domains. This is achieved by: Using LLMs and symbolic tools to repeatedly generate and verify hypotheses from acquired experiences in a contrastive generality improvement approach. Utilizing memory-based monitoring to detect action errors of embodied agents in real-time and refine their knowledge, ultimately improving the agent's task performance and generalization across open-domain environments. NeSyC was evaluated across various benchmark environments, including ALFWorld, VirtualHome, Minecraft, RLBench, and real-world robotic tabletop scenarios. It demonstrated robust performance across dynamic open-domain environments and outperformed state-of-the-art methods, such as AutoGen, ReAct, and CLMASP, in task success rates. CSI Lab conducts research on network and cloud system optimization, autonomous driving of robots and drones, and other self-learning technologies by leveraging Embodied Agent, Reinforcement Learning, and Self-Learning. Contact Information:Professor Woo Hongwook | hwoo@skku.edu | CSI Lab | https://sites.google.com/view/csi-agent-group
- 작성일 2025-02-20
- 조회수 7088
[Research] Security Engineering Lab, Two Papers Accepted at CHI 2025

[25.01.21] Security Engineering Lab, Two Papers Accepted at CHI 2025 The Security Engineering Lab (Advisor: Professor Hyungsik Kim) has had two papers accepted at CHI 2025 (ACM SIGCHI Conference on Human Factors in Computing Systems), one of the top-tier conferences in the field of Human-Computer Interaction (HCI). The papers will be presented in April 2025 in Yokohama, Japan. 1. Paper: "Understanding and Improving User Adoption and Security Awareness in Password Checkup Services" Authors: Sanghak Oh (PhD Student, Department of Electrical and Computer Engineering) Heewon Baek (MS Student, Department of Electrical and Computer Engineering) Taeyoung Kim (PhD Student, Department of Electrical and Computer Engineering) Woojin Jeon (PhD Student, Department of Electrical and Computer Engineering) Junho Heo (Samsung Research) Professor Ian Oakley (KAIST) Professor Hyungsik Kim (Sungkyunkwan University) Password Checkup Services (PCS) help users protect accounts by identifying compromised, reused, or weak passwords. However, these services have low adoption rates. This study conducted an online survey (N=238) to identify factors influencing PCS adoption and barriers to changing compromised passwords. Key findings include: Adoption factors: Perceived usefulness, ease of use, and self-efficacy were significant motivators. Barriers to password changes: Warning fatigue from frequent alerts, low awareness of password compromise risks, and reliance on other security measures discouraged users from taking action. To address these issues, the research team redesigned the PCS interface by: Clarifying warning messages related to compromised passwords. Automating the password change process, such as enabling users to update multiple reused passwords simultaneously or directly linking to password change pages. A task-based interview study (N=50) validated the effectiveness of the new design, showing a significant increase in password change rates in two scenarios: 40% and 74% change rates, compared to 16% and 60% in Google's existing PCS design. 2. Paper: "I Was Told to Install the Antivirus App, but I’m Not Sure I Need It: Understanding the Adoption, Discontinuation, and Non-Use of Smartphone Antivirus Software in South Korea" Authors: Seyoung Jin (MS Student, Department of Software) Heewon Baek (MS Student, Department of Software) Professor Euijin Lee (KAIST) Professor Hyungsik Kim (Sungkyunkwan University) This study investigates the limited effectiveness of smartphone antivirus software, despite recommendations from security firms, due to user misconceptions, regulatory requirements, and improper usage. Using a mixed-methods approach, including in-depth interviews (N=23) and a survey (N=250), the study examined the adoption status of smartphone antivirus software, particularly in South Korea, where it is often mandatory for banking and financial apps. Key findings: Many users confused antivirus software with general security tools and were unaware of its limited scope in addressing mobile malware threats. Factors influencing adoption: Perceived vulnerability, response efficacy, self-efficacy, social norms, and awareness. Factors leading to discontinuation or non-use: Concerns about system performance impact and skepticism about necessity. Additionally, the mandatory installation of antivirus software for financial apps in South Korea has contributed to user misconceptions, negative perceptions, and a false sense of security. This research highlights the need for better user education, clearer communication on mobile-specific security threats, and improved guidance to enhance effective antivirus software usage.
- 작성일 2025-02-20
- 조회수 6545