Picture for Zhipeng Wei

Zhipeng Wei

Emoji Attack: A Method for Misleading Judge LLMs in Safety Risk Detection

Add code
Nov 01, 2024
Viaarxiv icon

ReToMe-VA: Recursive Token Merging for Video Diffusion-based Unrestricted Adversarial Attack

Add code
Aug 10, 2024
Viaarxiv icon

Reliable and Efficient Concept Erasure of Text-to-Image Diffusion Models

Add code
Jul 17, 2024
Viaarxiv icon

Incorporating Locality of Images to Generate Targeted Transferable Adversarial Examples

Add code
Sep 08, 2022
Figure 1 for Incorporating Locality of Images to Generate Targeted Transferable Adversarial Examples
Figure 2 for Incorporating Locality of Images to Generate Targeted Transferable Adversarial Examples
Figure 3 for Incorporating Locality of Images to Generate Targeted Transferable Adversarial Examples
Figure 4 for Incorporating Locality of Images to Generate Targeted Transferable Adversarial Examples
Viaarxiv icon

Cross-Modal Transferable Adversarial Attacks from Images to Videos

Add code
Dec 10, 2021
Figure 1 for Cross-Modal Transferable Adversarial Attacks from Images to Videos
Figure 2 for Cross-Modal Transferable Adversarial Attacks from Images to Videos
Figure 3 for Cross-Modal Transferable Adversarial Attacks from Images to Videos
Figure 4 for Cross-Modal Transferable Adversarial Attacks from Images to Videos
Viaarxiv icon

Attacking Video Recognition Models with Bullet-Screen Comments

Add code
Oct 29, 2021
Figure 1 for Attacking Video Recognition Models with Bullet-Screen Comments
Figure 2 for Attacking Video Recognition Models with Bullet-Screen Comments
Figure 3 for Attacking Video Recognition Models with Bullet-Screen Comments
Figure 4 for Attacking Video Recognition Models with Bullet-Screen Comments
Viaarxiv icon

Boosting the Transferability of Video Adversarial Examples via Temporal Translation

Add code
Oct 18, 2021
Figure 1 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Figure 2 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Figure 3 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Figure 4 for Boosting the Transferability of Video Adversarial Examples via Temporal Translation
Viaarxiv icon

Towards Transferable Adversarial Attacks on Vision Transformers

Add code
Sep 18, 2021
Figure 1 for Towards Transferable Adversarial Attacks on Vision Transformers
Figure 2 for Towards Transferable Adversarial Attacks on Vision Transformers
Figure 3 for Towards Transferable Adversarial Attacks on Vision Transformers
Figure 4 for Towards Transferable Adversarial Attacks on Vision Transformers
Viaarxiv icon

Heuristic Black-box Adversarial Attacks on Video Recognition Models

Add code
Nov 21, 2019
Figure 1 for Heuristic Black-box Adversarial Attacks on Video Recognition Models
Figure 2 for Heuristic Black-box Adversarial Attacks on Video Recognition Models
Figure 3 for Heuristic Black-box Adversarial Attacks on Video Recognition Models
Figure 4 for Heuristic Black-box Adversarial Attacks on Video Recognition Models
Viaarxiv icon