Noise injection-based method has been shown to be able to improve the robustness of artificial neural networks in previous work. In this work, we propose a novel noise injection-based training scheme for better model robustness. Specifically, we first develop a likelihood ratio method to estimate the gradient with respect to both synaptic weights and noise levels for stochastic gradient descent training. Then, we design an approximation for the vanilla noise injection-based training method to reduce memory and improve computational efficiency. Next, we apply our proposed scheme to spiking neural networks and evaluate the performance of classification accuracy and robustness on MNIST and Fashion-MNIST datasets. Experiment results show that our proposed method achieves a much better performance on adversarial robustness and slightly better performance on original accuracy, compared with the conventional gradient-based training method.
Anticorrelated Noise Injection for Improved Generalization
ETH Zurich(苏黎世联邦理工学院);INRIA(法国国家信息与自动化研究所);Ecole Normale Supérieure(巴黎高等师范学院);PSL Research University(巴黎文理研究大学);University of Oslo(奥斯陆大学);University of Basel(巴塞尔大学)
Enhancing Neural Network Robustness Against Fault Injection Through Non-linear Weight Transformations
Kyushu Institute of Technology(九州工业大学);Graduate School of Life Science and Systems(生命科学与系统研究生院);Research Center for Neuromorphic AI Hardware(神经形态AI硬件研究中心)
Learning Without Adversarial Training: A Physics-Informed Neural Network for Secure Power System State Estimation under False Data Injection Attacks
KIOS Center of Excellence, University of Cyprus(塞浦路斯大学KIOS研究中心);CEMSE, KAUST(卡塔尔大学能源科学与工程学院);KIOS Center of Excellence, ECE Dept., University of Cyprus(塞浦路斯大学KIOS研究中心电子与计算机工程系)
RAISED: Self-Distillation for Robustness to Prompt Injection in LLM Agents
École polytechnique(巴黎综合理工学院);Institut Polytechnique de Paris(巴黎理工学院);CNRS(法国国家科学研究中心);Google DeepMind(谷歌DeepMind);Agence Ministérielle pour l’IA de Défense(法国国防部人工智能局);IRT SystemX(法国系统X技术研究所)
Training More Robust Classification Model via Discriminative Loss and Gaussian Noise Injection
Ampere Software Technology(Ampere软件技术公司);Institut de mathématiques de Toulouse(图卢兹数学研究所);Institut de Recherche en Informatique de Toulouse(图卢兹计算机研究所);Laboratoire Jean Alexandre Dieudonné, Université Côte d’Azur(坎特伯雷大学Dieudonné实验室)
Evaluating the Impact of Radiographic Noise on Chest X-ray Semantic Segmentation and Disease Classification Using a Scalable Noise Injection Framework
The University of Texas Health Science Center at Houston(德克萨斯大学休斯顿健康科学中心);Stanford University School of Medicine(斯坦福大学医学院);Algoverse AI Research(Algoverse AI 研究院)
Noise-Robustness Through Noise: A Framework combining Asymmetric LoRA with Poisoning MoE
School of Information and Software Engineering, University of Electronic Science and Technology of China(信息与软件工程学院,电子科学与技术大学);School of Computer Science and Engineering, Central South University(计算机科学与工程学院,中南大学)
Task complexity shapes internal representations and robustness in neural networks
Universitat de Barcelona(巴塞罗那大学);Universitat de Barcelona Institute of Complex Systems(巴塞罗那大学复杂系统研究所);Center for Complex Networks and Systems Research(复杂网络与系统研究所以);ICREA
Noise Injection Node Regularization for Robust Learning
Raymond and Beverly Sackler School of Physics and Astronomy(雷蒙德与贝弗利·萨克勒物理与天文学院);Tel-Aviv University(特拉维夫大学);Berkeley Center for Theoretical Physics(伯克利理论物理中心);University of California, Berkeley(加州大学伯克利分校);NHETC, Department of Physics and Astronomy(物理与天文系新泽西高能理论中心(NHETC));Rutgers University(罗格斯大学)