Han Qiu

DeepSweep: An Evaluation Framework for Mitigating DNN Backdoor Attacks using Data Augmentation

2021

Public resources and services (e.g., datasets, training platforms, pre-trained models) have been widely adopted to ease the development of Deep Learning-based applications. However, if the third-party providers are untrusted, they can inject poisoned samples into …

Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

2021

Watermarking has become the tendency in protecting the intellectual property of DNN models. Recent works, from the adversary's perspective, attempted to subvert watermarking mechanisms by designing watermark removal attacks. However, these attacks mainly adopted sophisticated …

A General Framework for Defending Against Backdoor Attacks via Influence Graph

2021 · arXiv (Cornell University)

In this work, we propose a new and general framework to defend against backdoor attacks, inspired by the fact that attack triggers usually follow a \textsc{specific} type of attacking pattern, and therefore, poisoned training examples …

A Combination Method of Resampling and Random Forest for Imbalanced Data Classification

2022 · 2022 4th International Conference on Advances in Computer Technology, Information Science and Communications (CTISC)

In the research of imbalanced data classification, the resampling effect of the existing resampling and random forest combination technology is greatly affected by the characteristic dimension of the training set, resulting in the unsatisfactory classification …

Incremental Learning, Incremental Backdoor Threats

2022 · IEEE Transactions on Dependable and Secure Computing

Class incremental learning from a pre-trained DNN model is gaining lots of popularity. Unfortunately, the pre-trained model also introduces a new attack vector, which enables an adversary to inject a backdoor into it and further …

Surging currents: a systematic review of the literature on dynamic stakeholder engagements in higher education in the generative artificial intelligence era

2024 · Journal of Asian Public Policy

As Generative Artificial Intelligence (GAI) rapidly integrates into higher education, a critical question arises: should we focus on the technology’s potential or the essential role of stakeholders? While GAI offers transformative possibilities, its success hinges …

ObfusBFA: A Holistic Approach to Safeguarding DNNs From Different Types of Bit-Flip Attacks

2026

Bit-flip attacks (BFAs) represent a serious threat to Deep Neural Networks (DNNs), where flipping a small number of bits in the model parameters or binary code can significantly degrade the model accuracy or mislead the …