On Xing Tian and the Perseverance of Anti-China Sentiment Online

Hate Speech, Social Media

Quantifying and Mitigating Privacy Risks of Contrastive Learning

Attribute Inference Attack, Contrastive Learning, Membership Inference Attack

SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models

Dataset, model

Semi-Leak: Membership Inference Attacks Against Semi-supervised Learning

Membership Inference Attack, Semi-supervised Learning

SSLGuard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders

Self-supervised Learning, Watermark

Stealing Links from Graph Neural Networks

Graph Neural Network, Link Stealing Attack

Test-Time Poisoning Attacks Against Test-Time Adaptation Models

Adversarial Example, Poisoning, Test-Time Adaptation

Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models

Diffusion, Memes

You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content

LLM, Toxic Detection

区块链核心技术研究及其数据分析