activity
20172023
most citedSubgraph Federated Learning with Missing Neighbor Generation

75 citations · 205 across the 15 of their papers we have counts for

collaborators
Showing cs.CRShow all

10 papers · 1 filter

cs.CR2023

DiffusionShield: A Watermark for Copyright Protection against Generative Diffusion Models

Yingqian Cui, Jie Ren, Han Xu +5

Recently, Generative Diffusion Models (GDMs) have showcased their remarkable capabilities in learning and generating images. A large community of GDMs has naturally emerged, furthe…

cs.CR202323 cited

BadGPT: Exploring Security Vulnerabilities of ChatGPT via Backdoor Attacks to InstructGPT

Jiawen Shi, Yixin Liu, Pan Zhou +1

Recently, ChatGPT has gained significant attention in research due to its ability to interact with humans effectively. The core idea behind this model is reinforcement learning (RL…

cs.CR20234 cited

Backdoor Attacks to Pre-trained Unified Foundation Models

Zenghui Yuan, Yixin Liu, Kai Zhang +2

The rise of pre-trained unified foundation models breaks down the barriers between different modalities and tasks, providing comprehensive support to users with unified architectur…

cs.CR202319 cited

SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

Junfeng Guo, Yiming Li, Xun Chen +3

Deep neural networks (DNNs) are vulnerable to backdoor attacks, where adversaries embed a hidden backdoor trigger during the training process for malicious prediction manipulation.…

cs.CR20218 cited

DoubleStar: Long-Range Attack Towards Depth Estimation based Obstacle Avoidance in Autonomous Systems

Ce Zhou, Qiben Yan, Yan Shi +1

Depth estimation-based obstacle avoidance has been widely adopted by autonomous systems (drones and vehicles) for safety purpose. It normally relies on a stereo camera to automatic…

cs.CR20214 cited

Source Inference Attacks in Federated Learning

Hongsheng Hu, Zoran Salcic, Lichao Sun +2

Federated learning (FL) has emerged as a promising privacy-aware paradigm that allows multiple clients to jointly train a model without sharing their private data. Recently, many s…