104 citations · 203 across the 13 of their papers we have counts for
13 papers
Dialectics of Alignment: Harnessing Unsafe Knowledge for Dynamic Safety Routing
Maryam Hashemzadeh, Jerry Huang, Minseon Kim +2
The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmful prompts. While effective a…
Enhancing Variational Autoencoders with Smooth Robust Latent Encoding
Hyomin Lee, Minseon Kim, Sangwon Jang +2
Variational Autoencoders (VAEs) have played a key role in scaling up diffusion-based generative models, as in Stable Diffusion, yet questions regarding their robustness remain larg…
Optimizing Query Generation for Enhanced Document Retrieval in RAG
Hamin Koo, Minseon Kim, Sung Ju Hwang
Large Language Models (LLMs) excel in various language tasks but they often generate incorrect information, a phenomenon known as "hallucinations". Retrieval-Augmented Generation (…
Automatic Jailbreaking of the Text-to-Image Generative AI Systems
Minseon Kim, Hyomin Lee, Boqing Gong +2
Recent AI systems have shown extremely powerful performance, even surpassing human performance, on various tasks such as information retrieval, language generation, and image gener…
Context-dependent Instruction Tuning for Dialogue Response Generation
Jin Myung Kwak, Minseon Kim, Sung Ju Hwang
Recent language models have achieved impressive performance in natural language tasks by incorporating instructions with task input during fine-tuning. Since all samples in the sam…
Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations
Hyeonjeong Ha, Minseon Kim, Sung Ju Hwang
Recent neural architecture search (NAS) frameworks have been successful in finding optimal architectures for given conditions (e.g., performance or latency). However, they search f…
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
Hayeon Lee, Sohyun An, Minseon Kim +1
Distillation-aware Neural Architecture Search (DaNAS) aims to search for an optimal student architecture that obtains the best performance and/or efficiency when distilling the kno…
Learning Transferable Adversarial Robust Representations via Multi-view Consistency
Minseon Kim, Hyeonjeong Ha, Dong Bok Lee +1
Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversa…
Effective Targeted Attacks for Adversarial Self-Supervised Learning
Minseon Kim, Hyeonjeong Ha, Sooel Son +1
Recently, unsupervised adversarial training (AT) has been highlighted as a means of achieving robustness in models without any label information. Previous studies in unsupervised A…
Language Detoxification with Attribute-Discriminative Latent Space
Jin Myung Kwak, Minseon Kim, Sung Ju Hwang
Transformer-based Language Models (LMs) have achieved impressive results on natural language understanding tasks, but they can also generate toxic text such as insults, threats, an…
Consistency Regularization for Adversarial Robustness
Jihoon Tack, Sihyun Yu, Jongheon Jeong +3
Adversarial training (AT) is currently one of the most successful methods to obtain the adversarial robustness of deep neural networks. However, the phenomenon of robust overfittin…
Adversarial Self-Supervised Contrastive Learning
Minseon Kim, Jihoon Tack, Sung Ju Hwang
Existing adversarial learning approaches mostly use class labels to generate adversarial samples that lead to incorrect predictions, which are then used to augment the training of…
Progressive Face Super-Resolution via Attention to Facial Landmark
Deokyun Kim, Minseon Kim, Gihyun Kwon +1
Face Super-Resolution (SR) is a subfield of the SR domain that specifically targets the reconstruction of face images. The main challenge of face SR is to restore essential facial…