Neural polarizer: A lightweight and effective backdoor defense via purifying poisoned features
Recent studies have demonstrated the susceptibility of deep neural networks to backdoor
attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be …
attacks. Given a backdoored model, its prediction of a poisoned sample with trigger will be …
Shared adversarial unlearning: Backdoor mitigation by unlearning shared adversarial examples
Backdoor attacks are serious security threats to machine learning models where an
adversary can inject poisoned samples into the training set, causing a backdoored model …
adversary can inject poisoned samples into the training set, causing a backdoored model …
Enhancing fine-tuning based backdoor defense with sharpness-aware minimization
Backdoor defense, which aims to detect or mitigate the effect of malicious triggers introduced
by attackers, is becoming increasingly critical for machine learning security and integrity …
by attackers, is becoming increasingly critical for machine learning security and integrity …
Attacks in adversarial machine learning: A systematic survey from the life-cycle perspective
Adversarial machine learning (AML) studies the adversarial phenomenon of machine
learning, which may make inconsistent or unexpected predictions with humans. Some …
learning, which may make inconsistent or unexpected predictions with humans. Some …
Stealthy Backdoor Attack via Confidence-driven Sampling
Backdoor attacks facilitate unauthorized control in the testing stage by carefully injecting
harmful triggers during the training phase of deep neural networks. Previous works have …
harmful triggers during the training phase of deep neural networks. Previous works have …