model security

Poisoning Deep Learning Based Recommender Model in Federated Learning Scenarios IJCAI 2022 Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks EMNLP 2022 Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NeurIPS 2022 With False Friends Like These, Who Can Notice Mistakes? AAAI 2022 Adversarial Neuron Pruning Purifies Backdoored Deep Models NeurIPS 2021 Anti-Backdoor Learning: Training Clean Models on Poisoned Data NeurIPS 2021 Backdoor Attacks on Pre-trained Models by Layerwise Weight Poisoning EMNLP 2021 Black-Box Detection of Backdoor Attacks With Limited Information and Data ICCV 2021 Defending Multimodal Fusion Models Against Single-Source Adversaries CVPR 2021 Excess Capacity and Backdoor Poisoning NeurIPS 2021 Measuring data leakage in machine-learning models with Fisher information UAI 2021 Provably Secure Federated Learning against Malicious Clients AAAI 2021 Topological Detection of Trojaned Neural Networks NeurIPS 2021 Learning Model with Error -- Exposing the Hidden Model of BAYHENN IJCAI 2020 Multi-way Encoding for Robustness WACV 2020 Poison Attacks against Text Datasets with Conditional Adversarially Regularized Autoencoder EMNLP 2020 TBT: Targeted Neural Network Attack With Bit Trojan CVPR 2020 Towards Adversarially Robust Knowledge Graph Embeddings AAAI 2020 Weight Poisoning Attacks on Pretrained Models ACL 2020 Constructing Unrestricted Adversarial Examples with Generative Models NeurIPS 2018 Evaluating the Robustness of Neural Networks: An Extreme Value Theory Approach ICLR 2018 The Security of Latent Dirichlet Allocation AISTATS 2015