Shiqing Ma

9

Papers

22

Total Citations

Papers (9)

MLLM-as-a-Judge for Image Safety without Human Labeling

Continuous Concepts Removal in Text-to-image Diffusion Models

Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone

Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

Invisible Backdoor Attack against Self-supervised Learning

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift