6 citations · 20 across the 12 of their papers we have counts for
12 papers
T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language Models
Jaehyuk Jang, Minseok Seo, Seungju Cho +2
Vision-language models (VLMs) achieve strong zero-shot recognition, but they remain highly vulnerable to adversarial perturbations. Recent test-time adaptations improve robustness…
Safety-Aligned Weights Are Not Enough: Refusal-Teacher-Guided Finetuning Enhances Safety and Downstream Performance under Harmful Finetuning Attacks
Seokil Ham, Yubin Choi, Yujin Yang +3
While Finetuning-as-a-Service (FaaS) enables customization of Large Language Models (LLMs) using user data, this service is vulnerable to safety degradation when user data includes…
Long-tailed Adversarial Training with Self-Distillation
Seungju Cho, Hongsin Lee, Changick Kim
Adversarial training significantly enhances adversarial robustness, yet superior performance is predominantly achieved on balanced datasets. Addressing adversarial robustness in th…
Enhancing Robustness in Incremental Learning with Adversarial Training
Seungju Cho, Hongsin Lee, Changick Kim
Adversarial training is one of the most effective approaches against adversarial attacks. However, adversarial training has primarily been studied in scenarios where data for all c…
Indirect Gradient Matching for Adversarial Robust Distillation
Hongsin Lee, Seungju Cho, Changick Kim
Adversarial training significantly improves adversarial robustness, but superior performance is primarily attained with large models. This substantial performance gap for smaller m…
Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup
Junyoung Byun, Myung-Joon Kwon, Seungju Cho +2
Deep neural networks are widely known to be susceptible to adversarial examples, which can cause incorrect predictions through subtle input modifications. These adversarial example…
RainUNet for Super-Resolution Rain Movie Prediction under Spatio-temporal Shifts
Jinyoung Park, Minseok Son, Seungju Cho +2
This paper presents a solution to the Weather4cast 2022 Challenge Stage 2. The goal of the challenge is to forecast future high-resolution rainfall events obtained from ground rada…
Improving the Transferability of Targeted Adversarial Examples through Object-Based Diverse Input
Junyoung Byun, Seungju Cho, Myung-Joon Kwon +2
The transferability of adversarial examples allows the deception on black-box models, and transfer-based targeted attacks have attracted a lot of interest due to their practical ap…
Balancing Domain Experts for Long-Tailed Camera-Trap Recognition
Byeongjun Park, Jeongsoo Kim, Seungju Cho +2
Label distributions in camera-trap images are highly imbalanced and long-tailed, resulting in neural networks tending to be biased towards head-classes that appear frequently. Alth…
CAP-GAN: Towards Adversarial Robustness with Cycle-consistent Attentional Purification
Mingu Kang, Trung Quang Tran, Seungju Cho +1
Adversarial attack is aimed at fooling the target classifier with imperceptible perturbation. Adversarial examples, which are carefully crafted with a malicious purpose, can lead t…
Applying Tensor Decomposition to image for Robustness against Adversarial Attack
Seungju Cho, Tae Joon Jun, Mingu Kang +1
Nowadays the deep learning technology is growing faster and shows dramatic performance in computer vision areas. However, it turns out a deep learning based model is highly vulnera…
DAPAS : Denoising Autoencoder to Prevent Adversarial attack in Semantic Segmentation
Seungju Cho, Tae Joon Jun, Byungsoo Oh +1
Nowadays, Deep learning techniques show dramatic performance on computer vision area, and they even outperform human. But it is also vulnerable to some small perturbation called an…