Alert button
Picture for Xinlei He

Xinlei He

Alert button

SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models

Oct 19, 2023
Boyang Zhang, Zheng Li, Ziqing Yang, Xinlei He, Michael Backes, Mario Fritz, Yang Zhang

Viaarxiv icon

A Comprehensive Study of Privacy Risks in Curriculum Learning

Oct 16, 2023
Joann Qiongna Chen, Xinlei He, Zheng Li, Yang Zhang, Zhou Li

Viaarxiv icon

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

Aug 10, 2023
Xinlei He, Savvas Zannettou, Yun Shen, Yang Zhang

Figure 1 for You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
Figure 2 for You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
Figure 3 for You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
Figure 4 for You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content
Viaarxiv icon

Generated Graph Detection

Jun 13, 2023
Yihan Ma, Zhikun Zhang, Ning Yu, Xinlei He, Michael Backes, Yun Shen, Yang Zhang

Figure 1 for Generated Graph Detection
Figure 2 for Generated Graph Detection
Figure 3 for Generated Graph Detection
Figure 4 for Generated Graph Detection
Viaarxiv icon

Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis

Jun 13, 2023
Yihan Ma, Zhengyu Zhao, Xinlei He, Zheng Li, Michael Backes, Yang Zhang

Figure 1 for Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
Figure 2 for Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
Figure 3 for Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
Figure 4 for Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
Viaarxiv icon

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

May 23, 2023
Yiting Qu, Xinyue Shen, Xinlei He, Michael Backes, Savvas Zannettou, Yang Zhang

Figure 1 for Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Figure 2 for Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Figure 3 for Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Figure 4 for Unsafe Diffusion: On the Generation of Unsafe Images and Hateful Memes From Text-To-Image Models
Viaarxiv icon

MGTBench: Benchmarking Machine-Generated Text Detection

Mar 26, 2023
Xinlei He, Xinyue Shen, Zeyuan Chen, Michael Backes, Yang Zhang

Figure 1 for MGTBench: Benchmarking Machine-Generated Text Detection
Figure 2 for MGTBench: Benchmarking Machine-Generated Text Detection
Figure 3 for MGTBench: Benchmarking Machine-Generated Text Detection
Figure 4 for MGTBench: Benchmarking Machine-Generated Text Detection
Viaarxiv icon

A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots

Feb 23, 2023
Boyang Zhang, Xinlei He, Yun Shen, Tianhao Wang, Yang Zhang

Figure 1 for A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Figure 2 for A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Figure 3 for A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Figure 4 for A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Viaarxiv icon

Fine-Tuning Is All You Need to Mitigate Backdoor Attacks

Dec 18, 2022
Zeyang Sha, Xinlei He, Pascal Berrang, Mathias Humbert, Yang Zhang

Figure 1 for Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Figure 2 for Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Figure 3 for Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Figure 4 for Fine-Tuning Is All You Need to Mitigate Backdoor Attacks
Viaarxiv icon

On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning

Dec 13, 2022
Yiting Qu, Xinlei He, Shannon Pierson, Michael Backes, Yang Zhang, Savvas Zannettou

Figure 1 for On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
Figure 2 for On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
Figure 3 for On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
Figure 4 for On the Evolution of (Hateful) Memes by Means of Multimodal Contrastive Learning
Viaarxiv icon