ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Jinyuan Jia

Jinyuan Jia

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 4:44 AM AMS

15

papers

219

total citations

papers (15)

PointGuard: Provably Robust 3D Point Cloud Classification

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

NEURIPS 2023arXiv

Data Poisoning based Backdoor Attacks to Contrastive Learning

MultiGuard: Provably Robust Multi-label Classification against Adversarial Examples

NEURIPS 2022arXiv

Graph Neural Network Explanations are Fragile

PointCert: Point Cloud Classification With Deterministic Certified Robustness Guarantees

Certifiably Robust Image Watermark

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

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

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

SHINE: Shielding Backdoors in Deep Reinforcement Learning

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

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

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

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