conftrace_
← Keywords

backdoor defense

54 papers

Explore in graph

Co-occurring keywords

backdoor attack (377) adversarial learning (1592) neural network (6616) data poisoning (128) model security (118) deep neural network (1801) adversarial defense (324) model purification (7) trigger detection (28) neural network security (46)

Papers

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness NIPS 2024
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense NIPS 2024
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space ACL 2024
Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor NIPS 2024
From Shortcuts to Triggers: Backdoor Defense with Denoised PoE NAACL 2024
PointCVaR: Risk-Optimized Outlier Removal for Robust 3D Point Cloud Classification AAAI 2024
LT-Defense: Searching-free Backdoor Defense via Exploiting the Long-tailed Effect NIPS 2024
BadActs: A Universal Backdoor Defense in the Activation Space ACL 2024
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack NIPS 2024
Backdoor Defense via Adaptively Splitting Poisoned Dataset CVPR 2023
On the Vulnerability of Backdoor Defenses for Federated Learning AAAI 2023
Enhancing Fine-Tuning Based Backdoor Defense with Sharpness-Aware Minimization ICCV 2023
TIJO: Trigger Inversion with Joint Optimization for Defending Multimodal Backdoored Models ICCV 2023
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples NIPS 2023
Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features NIPS 2023
Backdoor Defense via Deconfounded Representation Learning CVPR 2023
Backdoor Cleansing With Unlabeled Data CVPR 2023
Single Image Backdoor Inversion via Robust Smoothed Classifiers CVPR 2023
Reconstructive Neuron Pruning for Backdoor Defense ICML 2023
Towards Stable Backdoor Purification through Feature Shift Tuning NIPS 2023
WeDef: Weakly Supervised Backdoor Defense for Text Classification EMNLP 2022
BackdoorBench: A Comprehensive Benchmark of Backdoor Learning NIPS 2022
Moderate-fitting as a Natural Backdoor Defender for Pre-trained Language Models NIPS 2022
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training NIPS 2022