397 citations · 926 across the 49 of their papers we have counts for
16 papers · 1 filter
Test-Time Poisoning Attacks Against Test-Time Adaptation Models
Tianshuo Cong, Xinlei He, Yun Shen +1
Deploying machine learning (ML) models in the wild is challenging as it suffers from distribution shifts, where the model trained on an original domain cannot generalize well to un…
Mondrian: Prompt Abstraction Attack Against Large Language Models for Cheaper API Pricing
Wai Man Si, Michael Backes, Yang Zhang
The Machine Learning as a Service (MLaaS) market is rapidly expanding and becoming more mature. For example, OpenAI's ChatGPT is an advanced large language model (LLM) that generat…
Robustness Over Time: Understanding Adversarial Examples' Effectiveness on Longitudinal Versions of Large Language Models
Yugeng Liu, Tianshuo Cong, Zhengyu Zhao +3
Large Language Models (LLMs) undergo continuous updates to improve user experience. However, prior research on the security and safety implications of LLMs has primarily focused on…
Generated Graph Detection
Yihan Ma, Zhikun Zhang, Ning Yu +4
Graph generative models become increasingly effective for data distribution approximation and data augmentation. While they have aroused public concerns about their malicious misus…
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…
Two-in-One: A Model Hijacking Attack Against Text Generation Models
Wai Man Si, Michael Backes, Yang Zhang +1
Machine learning has progressed significantly in various applications ranging from face recognition to text generation. However, its success has been accompanied by different attac…
FACE-AUDITOR: Data Auditing in Facial Recognition Systems
Min Chen, Zhikun Zhang, Tianhao Wang +2
Few-shot-based facial recognition systems have gained increasing attention due to their scalability and ability to work with a few face images during the model deployment phase. Ho…
A Plot is Worth a Thousand Words: Model Information Stealing Attacks via Scientific Plots
Boyang Zhang, Xinlei He, Yun Shen +2
Building advanced machine learning (ML) models requires expert knowledge and many trials to discover the best architecture and hyperparameter settings. Previous work demonstrates t…
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…
PrivTrace: Differentially Private Trajectory Synthesis by Adaptive Markov Model
Haiming Wang, Zhikun Zhang, Tianhao Wang +4
Publishing trajectory data (individual's movement information) is very useful, but it also raises privacy concerns. To handle the privacy concern, in this paper, we apply different…
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…
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…
On the Privacy Risks of Cell-Based NAS Architectures
Hai Huang, Zhikun Zhang, Yun Shen +3
Existing studies on neural architecture search (NAS) mainly focus on efficiently and effectively searching for network architectures with better performance. Little progress has be…
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…
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Zeyang Sha, Xinlei He, Ning Yu +2
Self-supervised representation learning techniques have been developing rapidly to make full use of unlabeled images. They encode images into rich features that are oblivious to do…