-
- [Research] Prof. Hyung Joon Koo's Research Lab Publishes a paper in IEEE Symposium on Security and Privacy 2024
- SecAI 연구실 (지도교수: 구형준)과 고려대학교 김휘강 교수 연구실에서 공동연구한 논문이 컴퓨터 보안 분야에서 최우수 학술대회(IF=4)인 IEEE Symposium on Security and Privacy 2024에 게재 승인되었습니다! Abstract. Fuzzing has demonstrated great success in bug discovery and plays a crucial role in software testing today. Despite the increasing popularity of fuzzing, automated root cause analysis (RCA) has drawn less attention. One of the recent advances in RCA is crash-based statistical debugging, which leverages the behavioral differences in program execution between crash-triggered and non-crashing inputs. Hence, obtaining non-crashing behaviors close to the original crash is crucial but challenging with previous approaches (e.g., fuzzing). In this paper, we present BENZENE, a practical end-to-end RCA system that facilitates a fully automated crash diagnosis. To this end, we introduce a novel technique, called under-constrained state mutation, that generates both crashing and non-crashing behaviors for effective and efficient RCA. We design and implement the BENZENE prototype, and evaluate it with 60 vulnerabilities in the wild. Our empirical results demonstrate that BENZENE not only surpasses in performance (i.e., root cause ranking), but also achieves superior results in both speed (4.6 times faster) and memory footprint (31.4 times less) on average than prior approaches.
-
- 작성일 2023-07-18
- 조회수 1400
-
- [Research] Moon Hak-joon, won the Excellence Award in the thesis of the Korean Society for Information Protection (CISC-S'23)
- Moon Hak-joon (1st author, Bachelor of Software) and Park Eun-joo (Ph.D. in Artificial Intelligence) of the Data-Based Convergence Security Laboratory (DASH Lab: https://dash-lab.github.io Professor Usaiman) won the Excellence Award at the Korea Information Protection Association Summer Conference. This study proposes a method of determining the authenticity of an identification card using a neural network to confirm the user's identity with high accuracy in non-face-to-face situations. Summary: Mobile identity authentication systems are widely used mainly for e-commerce and digital banking. In order to use the service non-face-to-face, identification cards such as resident registration cards and driver's licenses are photographed in the process of authenticating the user's identity. However, since it is not possible to confirm that the actual ID card is being photographed with the user's camera, it is necessary to determine the authenticity of the photographed ID card. In this paper, deep learning techniques were used to determine whether the user's remotely provided ID image was real or manipulated in a non-digital area (an image printed in high definition or an image printed on a monitor after shooting). In addition to RGB images as input from the model, we experimented using discrete Fourier transform and feature extraction techniques. When the authenticity of the ID image was determined using the learned model, a classification accuracy of up to 96.6% was achieved. Paper Name: A Study on the Manipulated Identification Method Using Artificial Neural Networks Author: Moon Hak-joon, Park Eun-joo, Kim Jung-ho, Yoon Kwan-sik*, Seo-yeon*, Woo Simon Seong-il *: Samsung SDS Congratulations for the award 논문명: 인공신경망을 이용한 조작된 신분증 탐지기법 연구 저자: 문학준, 박은주, 김정호, 윤관식*, 서연아*, 우사이먼성일 *: 삼성 SDS 수상을 축하드립니다.
-
- 작성일 2023-07-17
- 조회수 1299
-
- [Student] [Professor's Performance] Professor Woo Simon's lab undergraduate student, Moon Hak-Joon won the Excellence Award for th
- Moon Hak-joon (1st author, In Bachelor of Software) and Park Eun-joo (In Ph.D. in Artificial Intelligence) of the Data-Based Convergence Security Laboratory (DASH Lab: https://dash-lab.github.io Professor Usaiman) won the Excellence Award at the Korea Information Protection Association Summer Conference. This study proposes a method of determining the authenticity of an identification card using a neural network to confirm the user's identity with high accuracy in non-face-to-face situations. Summary: Mobile identity authentication systems are widely used mainly for e-commerce and digital banking. In order to use the service non-face-to-face, identification cards such as resident registration cards and driver's licenses are photographed in the process of authenticating the user's identity. However, since it is not possible to confirm that the actual ID card is being photographed with the user's camera, it is necessary to determine the authenticity of the photographed ID card. In this paper, deep learning techniques were used to determine whether the user's remotely provided ID image was real or manipulated in a non-digital area (an image printed in high definition or an image printed on a monitor after shooting). In addition to RGB images as input from the model, we experimented using discrete Fourier transform and feature extraction techniques. When the authenticity of the ID image was determined using the learned model, a classification accuracy of up to 96.6% was achieved. Paper Name: A Study on the Manipulated Identification Method Using Artificial Neural Networks Author: Moon Hak-joon, Park Eun-joo, Kim Jung-ho, Yoon Kwan-sik*, Seo-yeon*, Woo Simon Seong-il *: Samsung SDS
-
- 작성일 2023-07-10
- 조회수 826
-
- [Research] A paper from Prof. Jinkyu Lee’s Lab. (RTCL@SKKU) accepted in ACM Mobisys 2023
- A paper from RTCL@SKKU (Advisor: Jinkyu Lee) has been accepted in ACM Mobisys 2023. ACM Mobisys is the premier conference in mobile systems, in which around 40 papers are usually published every year. In this year, ACM Mobisys 2023 will be held in Helsinki, Finland. ACM Mobisys 2023 website: https://www.sigmobile.org/mobisys/2023/ RTCL@SKKU website: https://rtclskku.github.io/website/ - (Paper Title) MixMax: Leveraging Heterogeneous Batteries to Alleviate Low Battery Experience for Mobile Users - (Authors in RTCL@SKKU) Jaeheon Kwak (M.S. alumni, the first author), Prof. Jinkyu Lee (the co-corresponding author) - (Teaser) https://youtu.be/LPXcpKlQxa0 - (Abstract) Despite the physical advance of an existing single-cell battery system, mobile users are still suffering from low battery anxiety. With a careful analysis of users’ battery usage behavior collected for 19,855 hours, we propose a heterogeneous battery system, MixMax, consisting of three complementary battery types tailored to minimizing the low battery time. While composing a heterogeneous battery system opens up a chance to simultaneously improve the capacity and the charging speed, one must face non-trivial challenges to determine the ratio of enclosed batteries and charge/discharge policies during the run-time. They are highly dependent on each other, which entails almost infinite candidates for the choice. MixMax gracefully unwinds the dependencies as it formulates the decision-making problem into an optimization problem and decomposes it into multiple sub-problems instead. To evaluate MixMax, we fabricate coin-cell batteries and experiment with them to model an accurate battery emulator which sophisticatedly reproduces the dynamics of battery systems. Our experimental results demonstrate that MixMax can reduce the low battery time by up to 24.6% without compromising capacity, volume, weight, and more importantly, users’ battery usage behavior. In addition, we prototype MixMax on a smartphone, presenting the practicality of MixMax on mobile systems. Jinkyu Lee | jinkyu.lee@skku.edu | RTCL@SKKU | https://rtclskku.github.io/website/
-
- 작성일 2023-06-07
- 조회수 1073
-
- [Research] Prof. Hwang Sung Jae's Research Lab Publishes a papaer in ESEC FSE2023
- 황성재 교수 연구실(소프트웨어 보안 연구실, SoftSec@SKKU) ESEC/FSE 2023 논문 게제 승인 소프트웨어 보안 연구실 (지도교수: 황성재)에서 작성한 논문이 소프트웨어 공학 분야의 최상위 국제 학술대회인 FSE 2023 (30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering)에 게재 승인되었습니다. 본 논문 “EtherDiffer: Differential Testing on RPC Services of Ethereum Nodes” 은 2023년 12월 미국 샌프란시스코에서 발표될 예정입니다. [논문 정보] - EtherDiffer: Differential Testing on RPC Services of Ethereum Nodes - Shinhae Kim, and Sungjae Hwang - 30th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE 2023) [논문 요약] Blockchain is a distributed ledger that records transactions among users on top of a peer-to-peer network. While various blockchain platforms exist, Ethereum is the most popular general-purpose platform and its support of smart contracts led to a new form of applications called decentralized applications (DApps). A typical DApp has an off-chain frontend and on-chain backend architecture, and the frontend often needs interactions with the backend network, e.g., to acquire chain data or make transactions. Therefore, Ethereum nodes implement the official RPC specification and expose a uniform set of RPC methods to the frontend. However, the specification is not sufficient in two points: (1) lack of clarification for non-deterministic event handling, and (2) lack of specification for invalid-as-themselves arguments. To effectively disclose any deviations caused by the insufficiency, this paper introduces EtherDiffer that automatically performs differential testing on four major node implementations in terms of their RPC services. EtherDiffer detected 48 different classes of deviations including 11 implementation bugs such as crash and denial-of-service bugs. We reported 44 of the detected classes to the specification and node developers and received acknowledgements as well as bug patches.
-
- 작성일 2023-05-30
- 조회수 1000
-
- [Research] A paper of Computer Graphics Lab. (CGLab) is accepted to ACM SIGGRAPH 2023
- A paper of Computer Graphics Lab. (CGLab, Advisor: Sungkil Lee; the first author: Janghun Kim), entitled "Potentially Visible Hidden-Volume Rendering for Multi-View Warping," has been accepeted to ACM SIGGRAPH 2023. The paper is going to be presented at LA, USA, August, 2023. ACM SIGGRAPH is the most prestigious conference in Computer Graphics area. This paper is selected as a journal-track paper, and will be published in ACM Trasactions on Graphics, Volume 42, No. 4의 special issue. Abstract -------- This paper presents the model and rendering algorithm of Potentially Visible Hidden Volumes (PVHVs) for multi-view image warping. PVHVs are 3D volumes that are occluded at a known source view, but potentially visible at novel views. Given a bound of novel views, we define PVHVs using the edges of foreground fragments from the known view and the bound of novel views. PVHVs can be used to batch-test the visibilities of source fragments without iterating individual novel views in multi-fragment rendering, and thereby, cull redundant fragments prior to warping. We realize the model of PVHVs in Depth Peeling (DP). Our Effective Depth Peeling (EDP) can reduce the number of completely hidden fragments, capture important fragments early, and reduce warping cost. We demonstrate the benefit of our PVHVs and EDP in terms of memory, quality, and performance in multi-view warping.
-
- 작성일 2023-05-25
- 조회수 1149
-
- [Research] Prof. Park HoGun's Research Lab Publishes a paper in the SIGKDD 2023
- Exploiting Relation-aware Attribute Representation Learning in Knowledge Graph Embedding for Numerical Reasoning Sookyung Kim+, Gayoung Kim+, Ko Keun Kim, Suchan Park, Heesoo Jung, Hogun Park* ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2023. Full Paper (Research Track). [+ Means Equal Contribution.] [Abstract] Numerical reasoning is one of the essential tasks to support machine learning applications such as recommendation and information retrieval. The reasoning task aims to compare two items and infer the new facts (e.g., is taller than) by leveraging existing relational information and numerical attributes (e.g., the height of an entity) in knowledge graphs. However, most existing methods are limited to introducing new attribute encoders or additional losses to predict the numeric values and are not robust when numerical attributes are sparsely available. In this paper, we propose a novel graph embedding method named RAKGE, which enhances numerical reasoning on knowledge graphs. The proposed method includes relation-aware attribute representation learning, which can leverage the association between relations and their corresponding numerical attributes. Additionally, we introduce a robust self-supervised learning method to generate unseen positive and negative examples, thereby making our approach more reliable when numerical attributes are sparse. Evaluated on three real-world datasets, our proposed model outperforms state-of-the-art methods, achieving an improvement of up to 65.1% in Hits@1 and up to 52.6% in MRR compared to the best competitor.
-
- 작성일 2023-05-23
- 조회수 1097
-
- [Research] Prof. Lee JeeHyong's Research Lab Publishes Three papers in the ACL 2023
- 논문 #1: “DIP: Dead code Insertion based Black-box Attack for Programming Language Model”, ACL 2023 (인공지능학과 석박통합과정 나철원, 소프트웨어학과 박사과정 최윤석) 논문 #2: “BLOCSUM: Block Scope-based Source Code Summarization via Shared Block Representation”, Findings of ACL 2023 (소프트웨어학과 박사과정 최윤석, 인공지능학과 석사과정 김효준) 논문 #3: “CodePrompt: Task-Agnostic Prefix Tuning for Program and Language Generation”, Findings of ACL 2023 (소프트웨어학과 박사과정 최윤석) (논문 #1) [Abstract] Automatic processing of source code, such as code clone detection and software vulnerability detection, is very helpful to software engineers. Large pre-trained Programming Language (PL) models (such as CodeBERT, GraphCodeBERT, CodeT5, etc.), show very powerful performance on these tasks. However, these PL models are vulnerable to adversarial examples that are generated with slight perturbation. Unlike natural language, an adversarial example of code must be semantic-preserving and compilable. Due to the requirements, it is hard to directly apply the existing attack methods for natural language models. In this paper, we propose DIP (Dead code Insertion based Black-box Attack for Programming Language Model), a high-performance and efficient black-box attack method to generate adversarial examples using dead code insertion. We evaluate our proposed method on 9 victim downstream-task large code models. Our method outperforms the state-of-the-art black-box attack in both attack efficiency and attack quality, while generated adversarial examples are compiled preserving semantic functionality. (논문 #2) [Abstract] Code summarization, which aims to automatically generate natural language descriptions from source code, has become an essential task in software development for better program understanding. Abstract Syntax Tree (AST), which represents the syntax structure of the source code, is helpful when utilized together with the sequence of code tokens to improve the quality of code summaries. Recent works on code summarization attempted to capture the sequential and structural information of the source code, but they considered less the property that source code consists of multiple code blocks. In this paper, we propose BLOCSUM, BLOck scope-based source Code SUMmarization via shared block representation that utilizes block-scope information by representing various structures of the code block. We propose a shared block position embedding to effectively represent the structure of code blocks and merge both code and AST. Furthermore, we develop variant ASTs to learn rich information such as block and global dependencies of the source code. To prove our approach, we perform experiments on two real-world datasets, the Java dataset and the Python dataset. We demonstrate the effectiveness of BLOCSUM through various experiments, including ablation studies and a human evaluation. (논문 #3) [Abstract] In order to solve the inefficient parameter update and storage issues of fine-tuning in Natural Language Generation (NLG) tasks, prompt-tuning methods have emerged as lightweight alternatives. Furthermore, efforts to reduce the gap between pre-training and fine-tuning have shown successful results in low resource settings. As large Pre-trained Language Models (PLMs) for Program and Language Generation (PLG) tasks are constantly being developed, prompt tuning methods are necessary for the tasks. However, due to the gap between pre-train and fine-tuning different from PLMs for natural language, a prompt tuning method that reflects the traits of PLM for program language is needed. In this paper, we propose a Task-Agnostic prompt tuning method for the PLG tasks, CodePrompt, that combines Input-Dependent Prompt Template (to bridge the gap between pre-training and fine-tuning of PLMs for program and language) and Corpus-Specific Prefix Tuning (to efficiently update the parameters of PLMs for program and language). Also, we propose a method to provide more rich prefix word information for limited prefix lengths. We prove that our method is effective in three PLG tasks, not only in the full-data setting, but also in the low-resource setting and cross domain setting.
-
- 작성일 2023-05-23
- 조회수 1112
-
- [Research] [Research] A research paper of Professor Usaiman's Lab is approved by IJCAI 2023
- The paper "IMF: Integrating Matched Features Using Intellectual Logit in Knowledge Distillation" by DASH Laboratory (Advisor: Usaiman) Kim Jung-ho (Master degree in 2023) and Lee Han-bin (Master degree in 2022) will be published in the International Joint Conferences and Artificial Intelligence (JAI) in August 2023. Knowledge distillation (KD) is an effective method for transferring the knowledge of a teacher model to a student model, that aims to improve the latter's performance efficiently. Although generic knowledge distillation methods such as softmax representation distillation and intermediate feature matching have demonstrated improvements with various tasks, only marginal improvements are shown in student networks due to their limited model capacity. In this work, to address the student model's limitation, we propose a novel flexible KD framework, Integrating Matched Features using Attentive Logit in Knowledge Distillation (IMF). Our approach introduces an intermediate feature distiller (IFD) to improve the overall performance of the student model by directly distilling the teacher's knowledge into branches of student models. The generated output of IFD, which is trained by the teacher model, is effectively combined by attentive logit. We use only a few blocks of the student and the trained IFD during inference, requiring an equal or less number of parameters. Through extensive experiments, we demonstrate that IMF consistently outperforms other state-of-the-art methods with a large margin over the various datasets in different tasks without extra computation.
-
- 작성일 2023-05-04
- 조회수 1101
-
- [Research] [Research] A Research paper of Professor Woo Hong-wook's laboratory (CSI laboratory) is approved by the ICML 2023
- A paper by the CSI lab (supervisor: Woo Hong-wook) has been accepted in the ICML 2023 (Fortieth International Conference on Machine Learning), an excellent society in the field of artificial intelligence. The paper will be published in Hawaii in the U.S. in July 23. The paper "One-shot Imagination in a Non-Stationary Environment via Multi-Modal Skill" includes software researchers Shin Sang-woo (graduate student), Lee Dae-hee (graduate student), Yoo Min-jong (graduate student), and Kim Woo-kyung (graduate student) as authors. The CSI lab uses machine learning, reinforcement learning, and self-supervised learning to conduct network and cloud system optimization research, as well as robot and drone autonomous driving research. The research of this ICML 2023 paper is underway with the support of the People-centered Artificial Intelligence Core Source Technology Project (IITP) and the Korea Research Foundation's Personal Basic Project (NRF).
-
- 작성일 2023-05-04
- 조회수 1215