19 citations · 42 across the 12 of their papers we have counts for
12 papers
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Yijun Yang, Ruiyuan Gao, Xiao Yang +2
Recent advancements in Text-to-Image (T2I) models have raised significant safety concerns about their potential misuse for generating inappropriate or Not-Safe-For-Work (NSFW) cont…
Non-Cross Diffusion for Semantic Consistency
Ziyang Zheng, Ruiyuan Gao, Qiang Xu
In diffusion models, deviations from a straight generative flow are a common issue, resulting in semantic inconsistencies and suboptimal generations. To address this challenge, we…
MMA-Diffusion: MultiModal Attack on Diffusion Models
Yijun Yang, Ruiyuan Gao, Xiaosen Wang +3
In recent years, Text-to-Image (T2I) models have seen remarkable advancements, gaining widespread adoption. However, this progress has inadvertently opened avenues for potential mi…
MagicDrive: Street View Generation with Diverse 3D Geometry Control
Ruiyuan Gao, Kai Chen, Enze Xie +4
Recent advancements in diffusion models have significantly enhanced the data synthesis with 2D control. Yet, precise 3D control in street view generation, crucial for 3D perception…
DiffGuard: Semantic Mismatch-Guided Out-of-Distribution Detection using Pre-trained Diffusion Models
Ruiyuan Gao, Chenchen Zhao, Lanqing Hong +1
Given a classifier, the inherent property of semantic Out-of-Distribution (OOD) samples is that their contents differ from all legal classes in terms of semantics, namely semantic…
Out-of-Distribution Detection with Semantic Mismatch under Masking
Yijun Yang, Ruiyuan Gao, Qiang Xu
This paper proposes a novel out-of-distribution (OOD) detection framework named MoodCat for image classifiers. MoodCat masks a random portion of the input image and uses a generati…
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation
Ailing Zeng, Xuan Ju, Lei Yang +4
This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any perform…
What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
Yijun Yang, Ruiyuan Gao, Yu Li +2
Adversarial examples (AEs) pose severe threats to the applications of deep neural networks (DNNs) to safety-critical domains, e.g., autonomous driving. While there has been a vast…
Relational Graph Neural Network Design via Progressive Neural Architecture Search
Ailing Zeng, Minhao Liu, Zhiwei Liu +3
We propose a novel solution to addressing a long-standing dilemma in the representation learning of graph neural networks (GNNs): how to effectively capture and represent useful in…
MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
Yijun Yang, Ruiyuan Gao, Yu Li +2
Machine learning with deep neural networks (DNNs) has become one of the foundation techniques in many safety-critical systems, such as autonomous vehicles and medical diagnosis sys…
ModuleNet: Knowledge-inherited Neural Architecture Search
Yaran Chen, Ruiyuan Gao, Fenggang Liu +1
Although Neural Architecture Search (NAS) can bring improvement to deep models, they always neglect precious knowledge of existing models. The computation and time costing property…
Privacy for Rescue: A New Testimony Why Privacy is Vulnerable In Deep Models
Ruiyuan Gao, Ming Dun, Hailong Yang +2
The huge computation demand of deep learning models and limited computation resources on the edge devices calls for the cooperation between edge device and cloud service by splitti…