Gradient Norm-based Fine-Tuning for Backdoor Defense in Automatic Speech Recognition
Backdoor attacks have posed a significant threat to the security of deep neural networks (DNNs). Despite considerable strides in developing defenses against backdoor attacks in the visual domain, the specialized defenses for the audio domain remain empty. Furthermore, the defenses adapted from the visual to audio domain demonstrate limited effectiveness. To fill this gap, we propose Gradient Norm-based FineTuning (GN-FT), a novel defense strategy against the attacks in the audio domain, based on the observation from the corresponding backdoored models. Specifically, we first empirically find that the backdoored neurons exhibit greater gradient values compared to other neurons, while clean neurons stay the lowest. On this basis, we fine-tune the backdoored model by incorporating the gradient norm regularization, aiming to weaken and reduce the backdoored neurons. We further approximate the loss computation for lower implementation costs. Extensive experiments on two speech recognition datasets across five models demonstrate the superior performance of our proposed method. To the best of our knowledge, this work is the first specialized and effective defense against backdoor attacks in the audio domain.
Code (0)
등록된 구현이 없습니다.
Tasks
Automatic Speech Recognitionbackdoor defensespeech-recognitionSpeech RecognitionSimilar Papers 제목 키워드 기반
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
The security threat of backdoor attacks is a central concern for deep neural networks (DNNs). Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdo…
backdoor defenseEnhancing 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. Fine-tuning based on benign data…
backdoor defenseGradient Broadcast Adaptation: Defending against the backdoor attack in pre-trained models
Pre-trained language models (e.g, BERT, GPT-3) have revolutionized the NLP research and fine-tuning becomes the indispensable step of downstream adaptation. However, the covert attack is the emerging threat to the pre-tr…
Backdoor Attacktext-classificationText ClassificationDefense against Backdoor Attacks via Identifying and Purifying Bad Neurons
The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones. In this paper, we propose …
backdoor defenseFine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
Deep neural networks (DNNs) provide excellent performance across a wide range of classification tasks, but their training requires high computational resources and is often outsourced to third parties. Recent work has sh…