Defense Through Diverse Directions
In this work we develop a novel Bayesian neural network methodology to achieve strong adversarial robustness without the need for online adversarial training. Unlike previous efforts in this direction, we do not rely solely on the stochasticity of network weights by minimizing the divergence between the learned parameter distribution and a prior. Instead, we additionally require that the model maintain some expected uncertainty with respect to all input covariates. We demonstrate that by encouraging the network to distribute evenly across inputs, the network becomes less susceptible to localized, brittle features which imparts a natural robustness to targeted perturbations. We show empirical robustness on several benchmark datasets.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial RobustnessSimilar Papers 제목 키워드 기반
Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks
Deep neural networks are increasingly deployed across heterogeneous and partially untrusted environments, where models are distributed through cloud storage, CI/CD pipelines, containerized services, and edge execution pl…
Privacy in Fine-tuning Large Language Models: Attacks, Defenses, and Future Directions
Fine-tuning has emerged as a critical process in leveraging Large Language Models (LLMs) for specific downstream tasks, enabling these models to achieve state-of-the-art performance across various domains. However, the f…
Federated LearningPrivacy PreservingDefense Against the Dark Arts: An overview of adversarial example security research and future research directions
This article presents a summary of a keynote lecture at the Deep Learning Security workshop at IEEE Security and Privacy 2018. This lecture summarizes the state of the art in defenses against adversarial examples and pro…
Deep LearningDistilling the Undistillable: Learning from a Nasty Teacher
The inadvertent stealing of private/sensitive information using Knowledge Distillation (KD) has been getting significant attention recently and has guided subsequent defense efforts considering its critical nature. Recen…
Knowledge DistillationBackdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions
Federated learning (FL) is a machine learning (ML) approach that allows the use of distributed data without compromising personal privacy. However, the heterogeneous distribution of data among clients in FL can make it d…
Backdoor AttackFederated LearningSurvey