4 papers
Exact Certification of Data-Poisoning Attacks Using Mixed-Integer Programming
Philip Sosnin, Jodie Knapp, Fraser Kennedy +2
This work introduces a verification framework that provides both sound and complete guarantees for data poisoning attacks during neural network training. We formulate adversarial d…
Detection of AI Generated Images Using Combined Uncertainty Measures and Particle Swarm Optimised Rejection Mechanism
Rahul Yumlembam, Biju Issac, Nauman Aslam +3
As AI-generated images become increasingly photorealistic, distinguishing them from natural images poses a growing challenge. This paper presents a robust detection framework that…
Abstract Gradient Training: A Unified Certification Framework for Data Poisoning, Unlearning, and Differential Privacy
Philip Sosnin, Matthew Wicker, Josh Collyer +1
The impact of inference-time data perturbation (e.g., adversarial attacks) has been extensively studied in machine learning, leading to well-established certification techniques fo…
Architectural Backdoors in Deep Learning: A Survey of Vulnerabilities, Detection, and Defense
Victoria Childress, Josh Collyer, Jodie Knapp
Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditiona…