conftrace_

backdoor attack

385 papers

Explore in graph

Also known as

BA

Co-occurring keywords

adversarial learning (1595) adversarial attack (1621) model security (118) data poisoning (128) neural network (6616) federated learning (1333) adversarial defense (325) poisoning attack (98) large language model (13587) neural network security (46)

Papers

BadPrompt: Backdoor Attacks on Continuous Prompts NIPS 2022
Finding Naturally Occurring Physical Backdoors in Image Datasets NIPS 2022
Dim-Krum: Backdoor-Resistant Federated Learning for NLP with Dimension-wise Krum-Based Aggregation EMNLP 2022
Fine-mixing: Mitigating Backdoors in Fine-tuned Language Models EMNLP 2022
DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints CVPR 2022
Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks EMNLP 2022
PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning IJCAI 2022
Backdoor Attacks in Federated Learning by Rare Embeddings and Gradient Ensembling EMNLP 2022
Quarantine: Sparsity Can Uncover the Trojan Attack Trigger for Free CVPR 2022
Dual-Key Multimodal Backdoors for Visual Question Answering CVPR 2022
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NIPS 2022
Neurotoxin: Durable Backdoors in Federated Learning ICML 2022
Effective Backdoor Defense by Exploiting Sensitivity of Poisoned Samples NIPS 2022
Data-Efficient Backdoor Attacks IJCAI 2022
Imperceptible Backdoor Attack: From Input Space to Feature Representation IJCAI 2022
BagFlip: A Certified Defense Against Data Poisoning NIPS 2022
Pre-activation Distributions Expose Backdoor Neurons NIPS 2022
Pass off Fish Eyes for Pearls: Attacking Model Selection of Pre-trained Models ACL 2022
Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection NIPS 2022
A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks NIPS 2022
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm NAACL 2022
Certified Robustness of Nearest Neighbors against Data Poisoning and Backdoor Attacks AAAI 2022
Sleeper Agent: Scalable Hidden Trigger Backdoors for Neural Networks Trained from Scratch NIPS 2022
Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models NIPS 2022
DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding AAAI 2022