87 citations · 125 across the 10 of their papers we have counts for
11 papers
Antibody: Strengthening Defense Against Harmful Fine-Tuning for Large Language Models via Attenuating Harmful Gradient Influence
Quoc Minh Nguyen, Trung Le, Jing Wu +2
Fine-tuning-as-a-service introduces a threat to Large Language Models' safety when service providers fine-tune their models on poisoned user-submitted datasets, a process known as…
IMU: Influence-guided Machine Unlearning
Xindi Fan, Jing Wu, Mingyi Zhou +3
Machine Unlearning (MU) aims to selectively erase the influence of specific data points from pretrained models. However, most existing MU methods rely on the retain set to preserve…
Investigating White-Box Attacks for On-Device Models
Mingyi Zhou, Xiang Gao, Jing Wu +3
Numerous mobile apps have leveraged deep learning capabilities. However, on-device models are vulnerable to attacks as they can be easily extracted from their corresponding mobile…
ModelObfuscator: Obfuscating Model Information to Protect Deployed ML-based Systems
Mingyi Zhou, Xiang Gao, Jing Wu +4
More and more edge devices and mobile apps are leveraging deep learning (DL) capabilities. Deploying such models on devices -- referred to as on-device models -- rather than as rem…
Concealing Sensitive Samples against Gradient Leakage in Federated Learning
Jing Wu, Munawar Hayat, Mingyi Zhou +1
Federated Learning (FL) is a distributed learning paradigm that enhances users privacy by eliminating the need for clients to share raw, private data with the server. Despite the s…
Performance Evaluation of Adversarial Attacks: Discrepancies and Solutions
Jing Wu, Mingyi Zhou, Ce Zhu +3
Recently, adversarial attack methods have been developed to challenge the robustness of machine learning models. However, mainstream evaluation criteria experience limitations, eve…
A Survey On Universal Adversarial Attack
Chaoning Zhang, Philipp Benz, Chenguo Lin +3
The intriguing phenomenon of adversarial examples has attracted significant attention in machine learning and what might be more surprising to the community is the existence of uni…
Decision-based Universal Adversarial Attack
Jing Wu, Mingyi Zhou, Shuaicheng Liu +2
A single perturbation can pose the most natural images to be misclassified by classifiers. In black-box setting, current universal adversarial attack methods utilize substitute mod…
ProbaNet: Proposal-balanced Network for Object Detection
Jing Wu, Xiang Zhang, Mingyi Zhou +1
Candidate object proposals generated by object detectors based on convolutional neural network (CNN) encounter easy-hard samples imbalance problem, which can affect overall perform…
Adversarial Imitation Attack
Mingyi Zhou, Jing Wu, Yipeng Liu +4
Deep learning models are known to be vulnerable to adversarial examples. A practical adversarial attack should require as little as possible knowledge of attacked models. Current s…
DaST: Data-free Substitute Training for Adversarial Attacks
Mingyi Zhou, Jing Wu, Yipeng Liu +2
Machine learning models are vulnerable to adversarial examples. For the black-box setting, current substitute attacks need pre-trained models to generate adversarial examples. Howe…