Jinyuan Jia

8

Papers

2

Total Citations

Papers (8)

VODiff: Controlling Object Visibility Order in Text-to-Image Generation

TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning

G2L-CariGAN: Caricature Generation from Global Structure to Local Features

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

MMCert: Provable Defense against Adversarial Attacks to Multi-modal Models

Data Poisoning based Backdoor Attacks to Contrastive Learning

SHINE: Shielding Backdoors in Deep Reinforcement Learning

Graph Neural Network Explanations are Fragile