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

Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks EMNLP 2022
Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense ICML 2022
Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks CVPR 2022
Backdoor Attacks on Self-Supervised Learning CVPR 2022
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning NIPS 2022
FIBA: Frequency-Injection Based Backdoor Attack in Medical Image Analysis CVPR 2022
Rethinking the Reverse-engineering of Trojan Triggers NIPS 2022
Provable Defense against Backdoor Policies in Reinforcement Learning NIPS 2022
Backdoor Attacks on the DNN Interpretation System AAAI 2022
Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models NAACL 2021
Adversarial Neuron Pruning Purifies Backdoored Deep Models NIPS 2021
DeHiB: Deep Hidden Backdoor Attack on Semi-supervised Learning via Adversarial Perturbation AAAI 2021
SPECTRE: defending against backdoor attacks using robust statistics ICML 2021
Black-Box Detection of Backdoor Attacks With Limited Information and Data ICCV 2021
Defending against Backdoors in Federated Learning with Robust Learning Rate AAAI 2021
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks ICCV 2021
CLEAR: Clean-Up Sample-Targeted Backdoor in Neural Networks ICCV 2021
Invisible Backdoor Attack With Sample-Specific Triggers ICCV 2021
Rethinking Stealthiness of Backdoor Attack against NLP Models ACL 2021
PointBA: Towards Backdoor Attacks in 3D Point Cloud ICCV 2021
Accumulative Poisoning Attacks on Real-time Data NIPS 2021
A Backdoor Attack Against 3D Point Cloud Classifiers ICCV 2021
Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger ACL 2021
Rethinking the Backdoor Attacks' Triggers: A Frequency Perspective ICCV 2021
Just How Toxic is Data Poisoning? A Unified Benchmark for Backdoor and Data Poisoning Attacks ICML 2021