Jiyoon Kim

Jiyoon Kim, Kentaro Toyama, Sangmi Kim et al.

Generative AI challenges academic integrity not only by enabling students to delegate substantial portions of their academic work, but also by blurring the ethical boundaries by which students distinguish acceptable assistance from misconduct. Drawing on semi-structured interviews (n=20), AI chat logs, and course documents (syllabi, submitted assignments), we investigated how students themselves make moral sense of AI use in academic writing. Our analysis results in a range of novel findings: First, there are at least five distinct sites of AI-use conceptualization, ranging from faculty's intended AI policy, to students' actual AI use. Second, students use over 20 distinct rationalizations to justify AI use, such as that copying AI-generated text is victimless; that any AI text reflecting their own beliefs or their own style is their own writing; or that they are learning more by using AI -- even extensively -- than otherwise. We present a taxonomy of these rationalizations, and show how some of them are employed to justify conscious violations of course policies. Third, student rationalizations occur in both an ad hoc and post hoc manner, and they are not necessarily self-consistent. These and other findings suggest that modern AI presents a steep, ethical, slippery slope which students conceptually slide down, landing far outside the pedagogical goals and expectations of instructors. We discuss implications for educational design and AI policy.

Eunsu Baek, Keondo Park, Jiyoon Kim et al.

Computer vision applications predict on digital images acquired by a camera from physical scenes through light. However, conventional robustness benchmarks rely on perturbations in digitized images, diverging from distribution shifts occurring in the image acquisition process. To bridge this gap, we introduce a new distribution shift dataset, ImageNet-ES, comprising variations in environmental and camera sensor factors by directly capturing 202k images with a real camera in a controllable testbed. With the new dataset, we evaluate out-of-distribution (OOD) detection and model robustness. We find that existing OOD detection methods do not cope with the covariate shifts in ImageNet-ES, implying that the definition and detection of OOD should be revisited to embrace real-world distribution shifts. We also observe that the model becomes more robust in both ImageNet-C and -ES by learning environment and sensor variations in addition to existing digital augmentations. Lastly, our results suggest that effective shift mitigation via camera sensor control can significantly improve performance without increasing model size. With these findings, our benchmark may aid future research on robustness, OOD, and camera sensor control for computer vision. Our code and dataset are available at https://github.com/Edw2n/ImageNet-ES.

Jiyoon Kim, Chuhong Wang, Aayush R. Singh et al.

The demand for safe, high-energy-density batteries has spotlighted halide solid-state electrolytes, which offer the potential for enhanced ionic mobility, electrochemical stability, and interfacial deformability. Accelerating their discovery requires extensive molecular dynamics, which has been increasingly enabled by universal machine learning interatomic potentials trained on foundational datasets. However, the dynamic softness of halides poses a stringent test of whether general-purpose models can reliably replace first-principles calculations under the highly distorted, elevated-temperature regimes necessary to probe ion transport. Here, we present AQVolt26, a dataset of 322,656 r$^2$SCAN single-point calculations for lithium halides, generated via high-temperature configurational sampling across $\sim$5K structures. We demonstrate that foundational datasets provide a strong baseline for stable halide chemistries and transfer local forces well, however absolute energy predictions degrade in distorted higher-temperature regimes. Co-training with AQVolt26 resolves this blind spot. Furthermore, incorporating Materials Project relaxation data improves near-equilibrium performance but degrades extreme-strain robustness without enhancing high-temperature force accuracy. These results demonstrate that domain-specific configurational sampling is essential for the reliable dynamic screening of halide electrolytes. Furthermore, our findings suggest that while foundational models provide a robust base, they are most effective for dynamically soft solid-state chemistries when augmented with targeted, high-temperature data. Finally, we show that near-equilibrium relaxation data serves as a task-specific complement rather than a universally beneficial addition.

Jiyoon Kim, Kang Eun Jeon, Yulhwa Kim et al.

Compute-in-memory (CIM) is an efficient method for implementing deep neural networks (DNNs) but suffers from substantial overhead from analog-to-digital converters (ADCs), especially as ADC precision increases. Low-precision ADCs can reduce this overhead but introduce partial-sum quantization errors degrading accuracy. Additionally, low-bit weight constraints, imposed by cell limitations and the need for multiple cells for higher-bit weights, present further challenges. While fine-grained partial-sum quantization has been studied to lower ADC resolution effectively, weight granularity, which limits overall partial-sum quantized accuracy, remains underexplored. This work addresses these challenges by aligning weight and partial-sum quantization granularities at the column-wise level. Our method improves accuracy while maintaining dequantization overhead, simplifies training by removing two-stage processes, and ensures robustness to memory cell variations via independent column-wise scale factors. We also propose an open-source CIM-oriented convolution framework to handle fine-grained weights and partial-sums efficiently, incorporating a novel tiling method and group convolution. Experimental results on ResNet-20 (CIFAR-10, CIFAR-100) and ResNet-18 (ImageNet) show accuracy improvements of 0.99%, 2.69%, and 1.01%, respectively, compared to the best-performing related works. Additionally, variation analysis reveals the robustness of our method against memory cell variations. These findings highlight the effectiveness of our quantization scheme in enhancing accuracy and robustness while maintaining hardware efficiency in CIM-based DNN implementations. Our code is available at https://github.com/jiyoonkm/ColumnQuant.

JungWoo Chae, Jiyoon Kim, JaeWoong Choi et al.

Personalizing diffusion models using limited data presents significant challenges, including overfitting, loss of prior knowledge, and degradation of text alignment. Overfitting leads to shifts in the noise prediction distribution, disrupting the denoising trajectory and causing the model to lose semantic coherence. In this paper, we propose Adaptive Personalized Training (APT), a novel framework that mitigates overfitting by employing adaptive training strategies and regularizing the model's internal representations during fine-tuning. APT consists of three key components: (1) Adaptive Training Adjustment, which introduces an overfitting indicator to detect the degree of overfitting at each time step bin and applies adaptive data augmentation and adaptive loss weighting based on this indicator; (2)Representation Stabilization, which regularizes the mean and variance of intermediate feature maps to prevent excessive shifts in noise prediction; and (3) Attention Alignment for Prior Knowledge Preservation, which aligns the cross-attention maps of the fine-tuned model with those of the pretrained model to maintain prior knowledge and semantic coherence. Through extensive experiments, we demonstrate that APT effectively mitigates overfitting, preserves prior knowledge, and outperforms existing methods in generating high-quality, diverse images with limited reference data.

Junha Park, Jaehui Hwang, Ian Ryu et al.

With advances in diffusion models, image generation has shown significant performance improvements. This raises concerns about the potential abuse of image generation, such as the creation of explicit or violent images, commonly referred to as Not Safe For Work (NSFW) content. To address this, the Stable Diffusion model includes several safety checkers to censor initial text prompts and final output images generated from the model. However, recent research has shown that these safety checkers have vulnerabilities against adversarial attacks, allowing them to generate NSFW images. In this paper, we find that these adversarial attacks are not robust to small changes in text prompts or input latents. Based on this, we propose SC-Pro (Spherical or Circular Probing), a training-free framework that easily defends against adversarial attacks generating NSFW images. Moreover, we develop an approach that utilizes one-step diffusion models for efficient NSFW detection (SC-Pro-o), further reducing computational resources. We demonstrate the superiority of our method in terms of performance and applicability.

Jiyoon Kim, Jie Cai, Srishti Gupta et al.

During community decision-making and civic collaboration, conflicts can escalate when people suspect misinformation. We introduce the concept of sense of misinformation as experiencing someone's language or behavior as misinformation when it is not, that is to say when no falsehood is involved. Misinformation and sense of misinformation feel similar and can have similar social consequences; but sense of misinformation rests upon a mistaken perception of someone else's information as false. Through a case study of a casino proposal in local community, we examine how sense of misinformation developed over time during a contentious civic process through key factors (i.e., miscoordination governance, miscommunication between local government and citizens, and conflict and the breakdown of civic discourse), undermining trust and community democracy. Distinguishing between misinformation and sense of misinformation presents a challenge, but it is important. We contribute a conceptual distinction to the misinformation literature by identifying this distinct phenomenon and discuss ways to help communities recognize and repair such misattributions. Finally, we discuss design approaches for mitigating sense of misinformation.

JungWoo Chae, Jiyoon Kim, Sangheum Hwang

Personalizing diffusion models to specific users or concepts remains challenging, particularly when only a few reference images are available. Existing methods such as DreamBooth and Textual Inversion often overfit to limited data, causing misalignment between generated images and text prompts when attempting to balance identity fidelity with prompt adherence. While Direct Consistency Optimization (DCO) with its consistency-guided sampling partially alleviates this issue, it still struggles with complex or stylized prompts. In this paper, we propose a parallel rescaling technique for personalized diffusion models. Our approach explicitly decomposes the consistency guidance signal into parallel and orthogonal components relative to classifier free guidance (CFG). By rescaling the parallel component, we minimize disruptive interference with CFG while preserving the subject's identity. Unlike prior personalization methods, our technique does not require additional training data or expensive annotations. Extensive experiments show improved prompt alignment and visual fidelity compared to baseline methods, even on challenging stylized prompts. These findings highlight the potential of parallel rescaled guidance to yield more stable and accurate personalization for diverse user inputs.

Vishal Sharma, Jiyoon Kim, Yongho Ko et al.

Cellular (C) setups facilitate the connectivity amongst the devices with better provisioning of services to its users. Vehicular networks are one of the representative setups that aim at expanding their functionalities by using the available cellular systems like Long Term Evolution (LTE)-based Evolved Universal Terrestrial Radio Access Network (E-UTRAN) as well as the upcoming Fifth Generation (5G)-based functional architecture. The vehicular networks include Vehicle to Vehicle (V2V), Vehicle to Infrastructure (V2I), Vehicle to Pedestrian (V2P) and Vehicle to Network (V2N), all of which are referred to as Vehicle to Everything (V2X). 5G has dominated the vehicular network and most of the upcoming research is motivated towards the fully functional utilization of 5G-V2X. Despite that, credential management and edge-initiated security are yet to be resolved under 5G-V2X. To further understand the issue, this paper presents security management as a principle of sustainability and key-management. The performance tradeoff is evaluated with the key-updates required to maintain a secure connection between the vehicles and the 5G-terminals. The proposed approach aims at the utilization of high-speed mmWave-based backhaul for enhancing the security operations between the core and the sub-divided functions at the edge of the network through a dual security management framework. The evaluations are conducted using numerical simulations, which help to understand the impact on the sustainability of connections as well as identification of the fail-safe points for secure and fast operations. Furthermore, the evaluations help to follow the multiple tradeoffs of security and performance based on the metrics like mandatory key updates, the range of operations and the probability of connectivity.

Gaurav Choudhary, Jiyoon Kim, Vishal Sharma

The rapid involution of the mobile generation with incipient data networking capabilities and utilization has exponentially increased the data traffic volumes. Such traffic drains various key issues in 5G mobile backhaul networks. Security of mobile backhaul is of utmost importance; however, there are a limited number of articles, which have explored such a requirement. This paper discusses the potential design issues and key challenges of the secure 5G mobile backhaul architecture. The comparisons of the existing state-of-the-art solutions for secure mobile backhaul, together with their major contributions have been explored. Furthermore, the paper discussed various key issues related to Quality of Service (QoS), routing and scheduling, resource management, capacity enhancement, latency, security-management, and handovers using mechanisms like Software Defined Networking and millimeter Wave technologies. Moreover, the trails of research challenges and future directions are additionally presented.

Vishal Sharma, Jiyoon Kim, Soonhyun Kwon et al.

Internet of Things (IoT) aims at providing connectivity between every computing entity. However, this facilitation is also leading to more cyber threats which may exploit the presence of a vulnerability of a period of time. One such vulnerability is the zero-day threat that may lead to zero-day attacks which are detrimental to an enterprise as well as the network security. In this article, a study is presented on the zero-day threats for IoT networks and a context graph-based framework is presented to provide a strategy for mitigating these attacks. The proposed approach uses a distributed diagnosis system for classifying the context at the central service provider as well as at the local user site. Once a potential zero-day attack is identified, a critical data sharing protocol is used to transmit alert messages and reestablish the trust between the network entities and the IoT devices. The results show that the distributed approach is capable of mitigating the zero-day threats efficiently with 33% and 21% improvements in terms of cost of operation and communication overheads, respectively, in comparison with the centralized diagnosis system.