5 citations · 7 across the 11 of their papers we have counts for
11 papers
Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models
Kangwook Ko, Jaehyuk Jang, Wonjun Lee +2
Removing a specific individual's information from multimodal large language models (MLLMs) is often needed after deployment, but existing methods rely on a retain set, which is har…
AIM: Anchor Identity Features, Then Match for Multimodal Large Language Model Unlearning
Wonjun Lee, Jaehyuk Jang, Kangwook Ko +2
Multimodal large language models (MLLMs) can memorize identity-specific facts about people in their fine-tuning data, creating privacy risks when a person requests deletion. Existi…
Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting
Kihyun Kim, Hee-Seon Kim, Wonjun Lee +1
Batch prompting is a practical inference strategy for large language models, but its safety implications remain underexplored. We show that the success of batch prompting for utili…
Benign-to-Toxic Jailbreaking: Inducing Harmful Responses from Harmless Prompts
Hee-Seon Kim, Minbeom Kim, Wonjun Lee +2
Optimization-based jailbreaks typically adopt the Toxic-Continuation setting in large vision-language models (LVLMs), following the standard next-token prediction objective. In thi…
Exploiting Vision Encoder Vulnerabilities for Universal Adversarial Perturbations on Large Vision-Language Models
Hee-Seon Kim, Minbeom Kim, Seokil Ham +1
Large Vision-Language Models (LVLMs) have achieved remarkable performance on multimodal tasks but remain highly vulnerable to small adversarial perturbations in input images. Exist…
Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation
Seokil Ham, Hee-Seon Kim, Sangmin Woo +1
Despite the growing interest in Mamba architecture as a potential replacement for Transformer architecture, parameter-efficient fine-tuning (PEFT) approaches for Mamba remain large…
VideoMamba: Spatio-Temporal Selective State Space Model
Jinyoung Park, Hee-Seon Kim, Kangwook Ko +2
We introduce VideoMamba, a novel adaptation of the pure Mamba architecture, specifically designed for video recognition. Unlike transformers that rely on self-attention mechanisms…
Breaking Temporal Consistency: Generating Video Universal Adversarial Perturbations Using Image Models
Hee-Seon Kim, Minji Son, Minbeom Kim +2
As video analysis using deep learning models becomes more widespread, the vulnerability of such models to adversarial attacks is becoming a pressing concern. In particular, Univers…
PG-RCNN: Semantic Surface Point Generation for 3D Object Detection
Inyong Koo, Inyoung Lee, Se-Ho Kim +3
One of the main challenges in LiDAR-based 3D object detection is that the sensors often fail to capture the complete spatial information about the objects due to long distance and…
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…