Picture for Qizhang Feng

Qizhang Feng

Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment

Add code
Jul 08, 2024
Figure 1 for Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
Figure 2 for Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
Figure 3 for Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
Figure 4 for Exposing Privacy Gaps: Membership Inference Attack on Preference Data for LLM Alignment
Viaarxiv icon

Can Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic Stroke

Add code
Aug 04, 2023
Viaarxiv icon

Efficient GNN Explanation via Learning Removal-based Attribution

Add code
Jun 09, 2023
Viaarxiv icon

DEGREE: Decomposition Based Explanation For Graph Neural Networks

Add code
May 22, 2023
Viaarxiv icon

Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyond

Add code
Apr 27, 2023
Viaarxiv icon

Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking

Add code
Mar 20, 2023
Viaarxiv icon

Differentially Private Counterfactuals via Functional Mechanism

Add code
Aug 04, 2022
Figure 1 for Differentially Private Counterfactuals via Functional Mechanism
Figure 2 for Differentially Private Counterfactuals via Functional Mechanism
Figure 3 for Differentially Private Counterfactuals via Functional Mechanism
Figure 4 for Differentially Private Counterfactuals via Functional Mechanism
Viaarxiv icon

Fair Machine Learning in Healthcare: A Review

Add code
Jun 29, 2022
Figure 1 for Fair Machine Learning in Healthcare: A Review
Figure 2 for Fair Machine Learning in Healthcare: A Review
Figure 3 for Fair Machine Learning in Healthcare: A Review
Figure 4 for Fair Machine Learning in Healthcare: A Review
Viaarxiv icon