Search Results for author:
Found 11 papers, 5 papers with code
Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift
Diffusion models (DM) have become state-of-the-art generative models because of their capability to generate high-quality images from noises without adversarial training.
POSIT: Promotion of Semantic Item Tail via Adversarial Learning
We subsequently use that metric in an adversarial learning framework to systematically promote disadvantaged items.
BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense
Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks.
MEDIC: Remove Model Backdoors via Importance Driven Cloning
It trains the clone model from scratch on a very small subset of samples and aims to minimize a cloning loss that denotes the differences between the activations of important neurons across the two models.
FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
In this work, we theoretically analyze the connection among cross-entropy loss, attack success rate, and clean accuracy in this setting.
DECK: Model Hardening for Defending Pervasive Backdoors
As such, using the samples derived from our attack in adversarial training can harden a model against these backdoor vulnerabilities.
Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense
We develop a novel optimization method for NLPbackdoor inversion.
Bounded Adversarial Attack on Deep Content Features
We propose a novel adversarial attack targeting content features in some deep layer, that is, individual neurons in the layer.
Better Trigger Inversion Optimization in Backdoor Scanning
A popular trigger inversion method is by optimization.
Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
By iteratively and stochastically selecting the most promising labels for optimization with the guidance of an objective function, we substantially reduce the complexity, allowing to handle models with many classes.
A Le Cam Type Bound for Adversarial Learning and Applications
Robustness of machine learning methods is essential for modern practical applications.
