Dong, Yinpeng
58 publications
NeurIPS
2025
DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-World Scenarios
ICCV
2025
Efficient Input-Level Backdoor Defense on Text-to-Image Synthesis via Neuron Activation Variation
ICML
2024
Efficient Black-Box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior
NeurIPS
2024
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
NeurIPS
2024
MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models
ECCV
2022
Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks
ICML
2022
GSmooth: Certified Robustness Against Semantic Transformations via Generalized Randomized Smoothing
ICMLW
2021
Boosting Transferability of Targeted Adversarial Examples via Hierarchical Generative Networks