Picture for Dong Lu

Dong Lu

Test-Time Backdoor Attacks on Multimodal Large Language Models

Add code
Feb 13, 2024
Viaarxiv icon

Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models

Add code
Jul 26, 2023
Viaarxiv icon

Detect All Abuse! Toward Universal Abusive Language Detection Models

Add code
Oct 09, 2020
Figure 1 for Detect All Abuse! Toward Universal Abusive Language Detection Models
Figure 2 for Detect All Abuse! Toward Universal Abusive Language Detection Models
Figure 3 for Detect All Abuse! Toward Universal Abusive Language Detection Models
Figure 4 for Detect All Abuse! Toward Universal Abusive Language Detection Models
Viaarxiv icon