Hunmin Yang
YOU?
Author Swipe
View article: Improving Black-Box Generative Attacks via Generator Semantic Consistency
Improving Black-Box Generative Attacks via Generator Semantic Consistency Open
Transfer attacks optimize on a surrogate and deploy to a black-box target. While iterative optimization attacks in this paradigm are limited by their per-input cost limits efficiency and scalability due to multistep gradient updates for ea…
View article: Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks
Prompt-Driven Contrastive Learning for Transferable Adversarial Attacks Open
Recent vision-language foundation models, such as CLIP, have demonstrated superior capabilities in learning representations that can be transferable across diverse range of downstream tasks and domains. With the emergence of such powerful …
View article: FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks Open
Deep neural networks are known to be vulnerable to security risks due to the inherent transferable nature of adversarial examples. Despite the success of recent generative model-based attacks demonstrating strong transferability, it still …
View article: Synthetic Image Generation for Military Vehicle Detection
Synthetic Image Generation for Military Vehicle Detection Open
This research paper investigates the effectiveness of using computer graphics(CG) based synthetic data for deep learning in military vehicle detection. In particular, we explore the use of synthetic image generation techniques to train dee…
View article: FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks
FACL-Attack: Frequency-Aware Contrastive Learning for Transferable Adversarial Attacks Open
Deep neural networks are known to be vulnerable to security risks due to the inherent transferable nature of adversarial examples. Despite the success of recent generative model-based attacks demonstrating strong transferability, it still …
View article: Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild
Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild Open
Recent monocular 3D shape reconstruction methods have shown promising zero-shot results on object-segmented images without any occlusions. However, their effectiveness is significantly compromised in real-world conditions, due to imperfect…
View article: ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion
ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion Open
Adversarial camouflage has garnered attention for its ability to attack object detectors from any viewpoint by covering the entire object's surface. However, universality and robustness in existing methods often fall short as the transfera…
View article: PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization
PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization Open
In a joint vision-language space, a text feature (e.g., from "a photo of a dog") could effectively represent its relevant image features (e.g., from dog photos). Also, a recent study has demonstrated the cross-modal transferability phenome…
View article: Camouflaged Adversarial Patch Attack on Object Detector
Camouflaged Adversarial Patch Attack on Object Detector Open
Adversarial attacks have received great attentions for their capacity to distract state-of-the-art neural networks by modifying objects in physical domain. Patch-based attack especially have got much attention for its optimization effectiv…
View article: DTA: Physical Camouflage Attacks using Differentiable Transformation Network
DTA: Physical Camouflage Attacks using Differentiable Transformation Network Open
To perform adversarial attacks in the physical world, many studies have proposed adversarial camouflage, a method to hide a target object by applying camouflage patterns on 3D object surfaces. For obtaining optimal physical adversarial cam…
View article: Synthetic Image Dataset Generation for Defense using Generative Adversarial Networks
Synthetic Image Dataset Generation for Defense using Generative Adversarial Networks Open