paper-with-me

Papers Malicious Detection

“Malicious Detection” 태그가 달린 논문 4편 · 필터 해제

AGATE: Stealthy Black-box Watermarking for Multimodal Model Copyright Protection

2025-04-28 · Jianbo Gao, Keke Gai, Jing Yu, Liehuang Zhu 외

Recent advancement in large-scale Artificial Intelligence (AI) models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distrib…

Adversarial AttackAnomaly Detectionimage-classificationImage Classification+3

Image Generation Network for Covert Transmission in Online Social Network

2022-07-21 · Zhengxin You, Qichao Ying, Sheng Li, Zhenxing Qian 외

Online social networks have stimulated communications over the Internet more than ever, making it possible for secret message transmission over such noisy channels. In this paper, we propose a Coverless Image Steganograp…

Image GenerationImage SteganographyMalicious DetectionSteganalysis

Backdoor Attack is a Devil in Federated GAN-based Medical Image Synthesis

2022-07-02 · Ruinan Jin, Xiaoxiao Li

Deep Learning-based image synthesis techniques have been applied in healthcare research for generating medical images to support open research. Training generative adversarial neural networks (GAN) usually requires large…

Backdoor AttackData PoisoningFederated LearningImage Generation+2

FAIR-BFL: Flexible and Incentive Redesign for Blockchain-based Federated Learning

2022-06-26 · Rongxin Xu, Shiva Raj Pokhrel, Qiujun Lan, Gang Li

Vanilla Federated learning (FL) relies on the centralized global aggregation mechanism and assumes that all clients are honest. This makes it a challenge for FL to alleviate the single point of failure and dishonest clie…

Federated LearningMalicious DetectionPhilosophy
1–4 / 4