backdoor attack

BagFlip: A Certified Defense Against Data Poisoning NeurIPS 2022 Better Trigger Inversion Optimization in Backdoor Scanning CVPR 2022 Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks AAAI 2022 Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense ICML 2022 Data-Efficient Backdoor Attacks IJCAI 2022 DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding AAAI 2022 DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints CVPR 2022 Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation EMNLP 2022 Dual-Key Multimodal Backdoors for Visual Question Answering CVPR 2022 Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples NeurIPS 2022 Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation IJCAI 2022 Exploring the Universal Vulnerability of Prompt-based Learning Paradigm NAACL 2022 Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks EMNLP 2022 FIBA: Frequency-Injection Based Backdoor Attack in Medical Image Analysis CVPR 2022 Finding Naturally Occurring Physical Backdoors in Image Datasets NeurIPS 2022 Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022 Foiling Training-Time Attacks on Neural Machine Translation Systems EMNLP 2022 Friendly Noise against Adversarial Noise: A Powerful Defense against Data Poisoning Attack NeurIPS 2022 Handcrafted Backdoors in Deep Neural Networks NeurIPS 2022 How to Inject Backdoors with Better Consistency: Logit Anchoring on Clean Data ICLR 2022 Imperceptible Backdoor Attack: From Input Space to Feature Representation IJCAI 2022 Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class NeurIPS 2022 Membership Inference via Backdooring IJCAI 2022 Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models NeurIPS 2022 Neurotoxin: Durable Backdoors in Federated Learning ICML 2022