neural network security

BppAttack: Stealthy and Efficient Trojan Attacks Against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning CVPR 2022 Complex Backdoor Detection by Symmetric Feature Differencing CVPR 2022 Deploying Convolutional Networks on Untrusted Platforms Using 2D Holographic Reduced Representations ICML 2022 Dual-Key Multimodal Backdoors for Visual Question Answering CVPR 2022 FIBA: Frequency-Injection Based Backdoor Attack in Medical Image Analysis CVPR 2022 On the Effectiveness of Small Input Noise for Defending Against Query-Based Black-Box Attacks WACV 2022 Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022 Randomized Channel Shuffling: Minimal-Overhead Backdoor Attack Detection without Clean Datasets NeurIPS 2022 Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NeurIPS 2022 Trap and Replace: Defending Backdoor Attacks by Trapping Them into an Easy-to-Replace Subnetwork NeurIPS 2022 A Backdoor Attack Against 3D Point Cloud Classifiers ICCV 2021 Anti-Backdoor Learning: Training Clean Models on Poisoned Data NeurIPS 2021 Backdoor Scanning for Deep Neural Networks through K-Arm Optimization ICML 2021 Black-Box Detection of Backdoor Attacks With Limited Information and Data ICCV 2021 CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks ICCV 2021 ONION: A Simple and Effective Defense Against Textual Backdoor Attacks EMNLP 2021 ProFlip: Targeted Trojan Attack With Progressive Bit Flips ICCV 2021 Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective ICCV 2021 Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution ACL 2021 WaNet - Imperceptible Warping-based Backdoor Attack ICLR 2021 TBT: Targeted Neural Network Attack With Bit Trojan CVPR 2020 Interpretation of Neural Networks Is Fragile AAAI 2019