Picture for Ruigang Liang

Ruigang Liang

MEA-Defender: A Robust Watermark against Model Extraction Attack

Add code
Jan 26, 2024
Viaarxiv icon

Boosting Neural Networks to Decompile Optimized Binaries

Add code
Jan 03, 2023
Viaarxiv icon

A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information

Add code
Oct 17, 2022
Figure 1 for A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information
Figure 2 for A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information
Figure 3 for A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information
Figure 4 for A Novel Membership Inference Attack against Dynamic Neural Networks by Utilizing Policy Networks Information
Viaarxiv icon

SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning

Add code
Sep 08, 2022
Figure 1 for SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Figure 2 for SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Figure 3 for SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Figure 4 for SSL-WM: A Black-Box Watermarking Approach for Encoders Pre-trained by Self-supervised Learning
Viaarxiv icon

Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain

Add code
Jul 09, 2022
Figure 1 for Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
Figure 2 for Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
Figure 3 for Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
Figure 4 for Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain
Viaarxiv icon

DBIA: Data-free Backdoor Injection Attack against Transformer Networks

Add code
Nov 22, 2021
Figure 1 for DBIA: Data-free Backdoor Injection Attack against Transformer Networks
Figure 2 for DBIA: Data-free Backdoor Injection Attack against Transformer Networks
Figure 3 for DBIA: Data-free Backdoor Injection Attack against Transformer Networks
Figure 4 for DBIA: Data-free Backdoor Injection Attack against Transformer Networks
Viaarxiv icon

HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks

Add code
Mar 25, 2021
Figure 1 for HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
Figure 2 for HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
Figure 3 for HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
Figure 4 for HufuNet: Embedding the Left Piece as Watermark and Keeping the Right Piece for Ownership Verification in Deep Neural Networks
Viaarxiv icon

Practical Adversarial Attack Against Object Detector

Add code
Dec 26, 2018
Figure 1 for Practical Adversarial Attack Against Object Detector
Figure 2 for Practical Adversarial Attack Against Object Detector
Figure 3 for Practical Adversarial Attack Against Object Detector
Figure 4 for Practical Adversarial Attack Against Object Detector
Viaarxiv icon