Picture for XiaoFeng Wang

XiaoFeng Wang

DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training

Add code
Mar 05, 2024
Viaarxiv icon

Malla: Demystifying Real-world Large Language Model Integrated Malicious Services

Add code
Jan 06, 2024
Viaarxiv icon

The Janus Interface: How Fine-Tuning in Large Language Models Amplifies the Privacy Risks

Add code
Oct 24, 2023
Viaarxiv icon

MAWSEO: Adversarial Wiki Search Poisoning for Illicit Online Promotion

Add code
Apr 22, 2023
Viaarxiv icon

Selective Amnesia: On Efficient, High-Fidelity and Blind Suppression of Backdoor Effects in Trojaned Machine Learning Models

Add code
Dec 09, 2022
Viaarxiv icon

Understanding Impacts of Task Similarity on Backdoor Attack and Detection

Add code
Oct 12, 2022
Figure 1 for Understanding Impacts of Task Similarity on Backdoor Attack and Detection
Figure 2 for Understanding Impacts of Task Similarity on Backdoor Attack and Detection
Figure 3 for Understanding Impacts of Task Similarity on Backdoor Attack and Detection
Figure 4 for Understanding Impacts of Task Similarity on Backdoor Attack and Detection
Viaarxiv icon

Towards Dark Jargon Interpretation in Underground Forums

Add code
Nov 05, 2020
Figure 1 for Towards Dark Jargon Interpretation in Underground Forums
Figure 2 for Towards Dark Jargon Interpretation in Underground Forums
Viaarxiv icon

Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints

Add code
Aug 22, 2018
Figure 1 for Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
Figure 2 for Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
Figure 3 for Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
Figure 4 for Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
Viaarxiv icon