8 papers
Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
Kealan Dunnett, Reza Arablouei, Dimity Miller +2
Backdoor attacks can implant malicious behaviours into deep models while preserving performance on clean data, posing a serious threat to safety-critical vision systems. Although b…
Unified Data Discovery across Query Modalities and User Intents
Tingting Wang, Shixun Huang, Zhifeng Bao +4
Data discovery - retrieving relevant tables from a data lake in response to user queries - is a fundamental building block for downstream analytics. In practice, data discovery mus…
Communication-Efficient Byzantine-Robust Federated Conformal Prediction via Partial Sharing
Ehsan Lari, Reza Arablouei, Stefan Werner
We propose PRISM-FCP (Partial shaRing and robust calIbration with Statistical Margins for Federated Conformal Prediction), a communication-efficient Byzantine-robust federated conf…
BadDet+: Robust Backdoor Attacks for Object Detection
Kealan Dunnett, Reza Arablouei, Dimity Miller +2
Backdoor attacks pose a severe threat to deep learning, yet their impact on object detection remains poorly understood compared to image classification. While attacks have been pro…
Backdoor Mitigation via Invertible Pruning Masks
Kealan Dunnett, Reza Arablouei, Dimity Miller +2
Model pruning has gained traction as a promising defense strategy against backdoor attacks in deep learning. However, existing pruning-based approaches often fall short in accurate…
Countering Backdoor Attacks in Image Recognition: A Survey and Evaluation of Mitigation Strategies
Kealan Dunnett, Reza Arablouei, Dimity Miller +2
The widespread adoption of deep learning across various industries has introduced substantial challenges, particularly in terms of model explainability and security. The inherent c…
Unlearning Backdoor Attacks through Gradient-Based Model Pruning
Kealan Dunnett, Reza Arablouei, Dimity Miller +2
In the era of increasing concerns over cybersecurity threats, defending against backdoor attacks is paramount in ensuring the integrity and reliability of machine learning models.…
Distinctiveness Maximization in Datasets Assemblage
Tingting Wang, Shixun Huang, Zhifeng Bao +3
In this paper, given a user's query set and budget, we aim to use the limited budget to help users assemble a set of datasets that can enrich a base dataset by introducing the maxi…