20 citations · 84 across the 21 of their papers we have counts for
23 papers
Amplifying Machine Learning Attacks Through Strategic Compositions
Yugeng Liu, Zheng Li, Hai Huang +2
Machine learning (ML) models are proving to be vulnerable to a variety of attacks that allow the adversary to learn sensitive information, cause mispredictions, and more. While the…
Watermarking LLM-Generated Datasets in Downstream Tasks
Yugeng Liu, Tianshuo Cong, Michael Backes +2
Large Language Models (LLMs) have experienced rapid advancements, with applications spanning a wide range of fields, including sentiment classification, review generation, and ques…
Membership Inference Attacks Against Vision-Language Models
Yuke Hu, Zheng Li, Zhihao Liu +4
Vision-Language Models (VLMs), built on pre-trained vision encoders and large language models (LLMs), have shown exceptional multi-modal understanding and dialog capabilities, posi…
: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities
Yukun Jiang, Zheng Li, Xinyue Shen +3
Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored. In th…
Membership Inference Attacks Against In-Context Learning
Rui Wen, Zheng Li, Michael Backes +1
Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learnin…
BadMerging: Backdoor Attacks Against Model Merging
Jinghuai Zhang, Jianfeng Chi, Zheng Li +3
Fine-tuning pre-trained models for downstream tasks has led to a proliferation of open-sourced task-specific models. Recently, Model Merging (MM) has emerged as an effective approa…
Inside the Black Box: Detecting Data Leakage in Pre-trained Language Encoders
Yuan Xin, Zheng Li, Ning Yu +4
Despite being prevalent in the general field of Natural Language Processing (NLP), pre-trained language models inherently carry privacy and copyright concerns due to their nature o…
Membership Inference Attack Against Masked Image Modeling
Zheng Li, Xinlei He, Ning Yu +1
Masked Image Modeling (MIM) has achieved significant success in the realm of self-supervised learning (SSL) for visual recognition. The image encoder pre-trained through MIM, invol…
SecurityNet: Assessing Machine Learning Vulnerabilities on Public Models
Boyang Zhang, Zheng Li, Ziqing Yang +4
While advanced machine learning (ML) models are deployed in numerous real-world applications, previous works demonstrate these models have security and privacy vulnerabilities. Var…
A Comprehensive Study of Privacy Risks in Curriculum Learning
Joann Qiongna Chen, Xinlei He, Zheng Li +2
Training a machine learning model with data following a meaningful order, i.e., from easy to hard, has been proven to be effective in accelerating the training process and achievin…
Generative Watermarking Against Unauthorized Subject-Driven Image Synthesis
Yihan Ma, Zhengyu Zhao, Xinlei He +3
Large text-to-image models have shown remarkable performance in synthesizing high-quality images. In particular, the subject-driven model makes it possible to personalize the image…
FDINet: Protecting against DNN Model Extraction via Feature Distortion Index
Hongwei Yao, Zheng Li, Haiqin Weng +3
Machine Learning as a Service (MLaaS) platforms have gained popularity due to their accessibility, cost-efficiency, scalability, and rapid development capabilities. However, recent…
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
Kai Mei, Zheng Li, Zhenting Wang +2
Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word…
Watermarking Diffusion Model
Yugeng Liu, Zheng Li, Michael Backes +2
The availability and accessibility of diffusion models (DMs) have significantly increased in recent years, making them a popular tool for analyzing and predicting the spread of inf…
Backdoor Attacks Against Dataset Distillation
Yugeng Liu, Zheng Li, Michael Backes +2
Dataset distillation has emerged as a prominent technique to improve data efficiency when training machine learning models. It encapsulates the knowledge from a large dataset into…
Backdoor Attacks in the Supply Chain of Masked Image Modeling
Xinyue Shen, Xinlei He, Zheng Li +3
Masked image modeling (MIM) revolutionizes self-supervised learning (SSL) for image pre-training. In contrast to previous dominating self-supervised methods, i.e., contrastive lear…
Membership Inference Attacks Against Text-to-image Generation Models
Yixin Wu, Ning Yu, Zheng Li +2
Text-to-image generation models have recently attracted unprecedented attention as they unlatch imaginative applications in all areas of life. However, developing such models requi…
UnGANable: Defending Against GAN-based Face Manipulation
Zheng Li, Ning Yu, Ahmed Salem +3
Deepfakes pose severe threats of visual misinformation to our society. One representative deepfake application is face manipulation that modifies a victim's facial attributes in an…
DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models
Zeyang Sha, Zheng Li, Ning Yu +1
Text-to-image generation models that generate images based on prompt descriptions have attracted an increasing amount of attention during the past few months. Despite their encoura…
Data Poisoning Attacks Against Multimodal Encoders
Ziqing Yang, Xinlei He, Zheng Li +4
Recently, the newly emerged multimodal models, which leverage both visual and linguistic modalities to train powerful encoders, have gained increasing attention. However, learning…
Auditing Membership Leakages of Multi-Exit Networks
Zheng Li, Yiyong Liu, Xinlei He +3
Relying on the fact that not all inputs require the same amount of computation to yield a confident prediction, multi-exit networks are gaining attention as a prominent approach fo…
Membership-Doctor: Comprehensive Assessment of Membership Inference Against Machine Learning Models
Xinlei He, Zheng Li, Weilin Xu +2
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to infer whether an input sample w…
Membership Leakage in Label-Only Exposures
Zheng Li, Yang Zhang
Machine learning (ML) has been widely adopted in various privacy-critical applications, e.g., face recognition and medical image analysis. However, recent research has shown that M…