Partial train and isolate, mitigate backdoor attack
Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories on the poisoned samples. Backdoor attacks are full of threats. Poisoned samples are becoming more and more similar to corresponding normal samples, and even the human eye cannot easily distinguish them. On the other hand, the accuracy of models carrying backdoors on normal samples is no different from that of clean models.In this article, by observing the characteristics of backdoor attacks, We provide a new model training method (PT) that freezes part of the model to train a model that can isolate suspicious samples. Then, on this basis, a clean model is fine-tuned to resist backdoor attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Backdoor AttackSimilar Papers 제목 키워드 기반
DeTrigger: A Gradient-Centric Approach to Backdoor Attack Mitigation in Federated Learning
Federated Learning (FL) enables collaborative model training across distributed devices while preserving local data privacy, making it ideal for mobile and embedded systems. However, the decentralized nature of FL also o…
Adversarial AttackBackdoor AttackFederated LearningModel PoisoningCL-Attack: Textual Backdoor Attacks via Cross-Lingual Triggers
Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fix…
Backdoor AttackSentenceModel Agnostic Defence against Backdoor Attacks in Machine Learning
Machine Learning (ML) has automated a multitude of our day-to-day decision making domains such as education, employment and driving automation. The continued success of ML largely depends on our ability to trust the mode…
BIG-bench Machine LearningDecision MakingGeneral Classificationimage-classification+2Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
Federated learning (FL) is vulnerable to backdoor attacks due to its distributed computing nature. Existing defense solution usually requires larger amount of computation in either the training or testing phase, which l…
backdoor defenseDistributed ComputingFederated LearningLockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training
Federated learning (FL) is vulnerable to backdoor attacks due to its distributed computing nature. Existing defense solution usually requires larger amount of computation in either the training or testing phase, which l…
backdoor defenseDistributed ComputingFederated Learning