backdoor defense
57 papers with code • 0 benchmarks • 2 datasets
Benchmarks
These leaderboards are used to track progress in backdoor defense
ULP Dataset
Most implemented papers
FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis
However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e. g., X-Ray, CT, and MRI) and analysis tasks (e. g., classification, detection, and segmentation).
ONION: A Simple and Effective Defense Against Textual Backdoor Attacks
Nevertheless, there are few studies on defending against textual backdoor attacks.
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks
pibo16/backdoor_attacks
•
•
ICCV 2021
Under this optimization framework, the trigger generator function will learn to manipulate the input with imperceptible noise to preserve the model performance on the clean data and maximize the attack success rate on the poisoned data.
Backdoor Defense via Decoupling the Training Process
Recent studies have revealed that deep neural networks (DNNs) are vulnerable to backdoor attacks, where attackers embed hidden backdoors in the DNN model by poisoning a few training samples.
Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples
shawkui/Shared_Adversarial_Unlearning
•
•
NeurIPS 2023
By establishing the connection between backdoor risk and adversarial risk, we derive a novel upper bound for backdoor risk, which mainly captures the risk on the shared adversarial examples (SAEs) between the backdoored model and the purified model.
Beating Backdoor Attack at Its Own Game
minliu01/non-adversarial_backdoor
•
•
ICCV 2023
Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added.
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Specifically, PDB leverages the home-field advantage of defenders by proactively injecting a defensive backdoor into the model during training.
Uncovering, Explaining, and Mitigating the Superficial Safety of Backdoor Defense
aisafety-hkust/stable_backdoor_purification
•
•
We find that current safety purification methods are vulnerable to the rapid re-learning of backdoor behavior, even when further fine-tuning of purified models is performed using a very small number of poisoned samples.
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training phase.
Clean-Label Backdoor Attacks on Video Recognition Models
ShihaoZhaoZSH/Video-Backdoor-Attack
•
•
CVPR 2020
We propose the use of a universal adversarial trigger as the backdoor trigger to attack video recognition models, a situation where backdoor attacks are likely to be challenged by the above 4 strict conditions.
