30 citations · 133 across the 49 of their papers we have counts for
10 papers · 1 filter
TranSegPGD: Improving Transferability of Adversarial Examples on Semantic Segmentation
Xiaojun Jia, Jindong Gu, Yihao Huang +4
Transferability of adversarial examples on image classification has been systematically explored, which generates adversarial examples in black-box mode. However, the transferabili…
JailGuard: A Universal Detection Framework for LLM Prompt-based Attacks
Xiaoyu Zhang, Cen Zhang, Tianlin Li +7
The systems and software powered by Large Language Models (LLMs) and Multi-Modal LLMs (MLLMs) have played a critical role in numerous scenarios. However, current LLM systems are vu…
AdapterFL: Adaptive Heterogeneous Federated Learning for Resource-constrained Mobile Computing Systems
Ruixuan Liu, Ming Hu, Zeke Xia +5
Federated Learning (FL) enables collaborative learning of large-scale distributed clients without data sharing. However, due to the disparity of computing resources among massive m…
FilterFL: Knowledge Filtering-based Data-Free Backdoor Defense for Federated Learning
Yanxin Yang, Ming Hu, Xiaofei Xie +4
As a distributed machine learning paradigm, Federated Learning (FL) enables large-scale clients to collaboratively train a model without sharing their raw data. However, due to the…
Towards Better Fairness-Utility Trade-off: A Comprehensive Measurement-Based Reinforcement Learning Framework
Simiao Zhang, Jitao Bai, Menghong Guan +4
Machine learning is widely used to make decisions with societal impact such as bank loan approving, criminal sentencing, and resume filtering. How to ensure its fairness while main…
On the Robustness of Segment Anything
Yihao Huang, Yue Cao, Tianlin Li +5
Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt…
Architecture-agnostic Iterative Black-box Certified Defense against Adversarial Patches
Di Yang, Yihao Huang, Qing Guo +4
The adversarial patch attack aims to fool image classifiers within a bounded, contiguous region of arbitrary changes, posing a real threat to computer vision systems (e.g., autonom…
Is Aggregation the Only Choice? Federated Learning via Layer-wise Model Recombination
Ming Hu, Zhihao Yue, Xiaofei Xie +6
Although Federated Learning (FL) enables global model training across clients without compromising their raw data, due to the unevenly distributed data among clients, existing Fede…
Personalization as a Shortcut for Few-Shot Backdoor Attack against Text-to-Image Diffusion Models
Yihao Huang, Felix Juefei-Xu, Qing Guo +6
Although recent personalization methods have democratized high-resolution image synthesis by enabling swift concept acquisition with minimal examples and lightweight computation, t…
Evading DeepFake Detectors via Adversarial Statistical Consistency
Yang Hou, Qing Guo, Yihao Huang +3
In recent years, as various realistic face forgery techniques known as DeepFake improves by leaps and bounds,more and more DeepFake detection techniques have been proposed. These m…