A Backdoor Approach with Inverted Labels Using Dirty Label-Flipping Attacks

arXiv:2404.00076v1 Announce Type: cross
Abstract: Audio-based machine learning systems frequently use public or third-party data, which might be inaccurate. This exposes deep neural network (DNN) models trained on such data to potential data poisoning attacks. In this type of assault, attackers can train the DNN model using poisoned data, potentially degrading its performance. Another type of data poisoning attack that is extremely relevant to our investigation is label flipping, in which the attacker manipulates the labels for a subset of …

abstract arxiv attacks audio backdoor cs.ai cs.cl cs.cr cs.lg data data poisoning deep neural network dnn eess.sp labels learning systems machine machine learning network neural network poisoning attacks public systems train type