Picture for Derui Wang

Derui Wang

Minhui

Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systems

Add code
Jul 11, 2024
Viaarxiv icon

QUEEN: Query Unlearning against Model Extraction

Add code
Jul 01, 2024
Figure 1 for QUEEN: Query Unlearning against Model Extraction
Figure 2 for QUEEN: Query Unlearning against Model Extraction
Figure 3 for QUEEN: Query Unlearning against Model Extraction
Figure 4 for QUEEN: Query Unlearning against Model Extraction
Viaarxiv icon

Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning

Add code
Jun 28, 2024
Figure 1 for Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning
Figure 2 for Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning
Figure 3 for Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning
Figure 4 for Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning
Viaarxiv icon

Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

Add code
Jun 04, 2024
Viaarxiv icon

Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer

Add code
May 15, 2024
Figure 1 for Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
Figure 2 for Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
Figure 3 for Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
Figure 4 for Towards Evaluating the Robustness of Automatic Speech Recognition Systems via Audio Style Transfer
Viaarxiv icon

Provably Unlearnable Examples

Add code
May 06, 2024
Viaarxiv icon

LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model

Add code
Mar 27, 2024
Figure 1 for LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Figure 2 for LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Figure 3 for LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Figure 4 for LocalStyleFool: Regional Video Style Transfer Attack Using Segment Anything Model
Viaarxiv icon

Reinforcement Unlearning

Add code
Dec 26, 2023
Viaarxiv icon

LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer

Add code
Dec 15, 2023
Figure 1 for LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
Figure 2 for LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
Figure 3 for LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
Figure 4 for LogoStyleFool: Vitiating Video Recognition Systems via Logo Style Transfer
Viaarxiv icon

Double-Flow-based Steganography without Embedding for Image-to-Image Hiding

Add code
Nov 25, 2023
Figure 1 for Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
Figure 2 for Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
Figure 3 for Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
Figure 4 for Double-Flow-based Steganography without Embedding for Image-to-Image Hiding
Viaarxiv icon