Enhancing Clean Label Backdoor Attack with Two-phase Specific Triggers
Backdoor attacks threaten Deep Neural Networks (DNNs). Towards stealthiness, researchers propose clean-label backdoor attacks, which require the adversaries not to alter the labels of the poisoned training datasets. Clean-label settings make the attack more stealthy due to the correct image-label pairs, but some problems still exist: first, traditional methods for poisoning training data are ineffective; second, traditional triggers are not stealthy which are still perceptible. To solve these problems, we propose a two-phase and image-specific triggers generation method to enhance clean-label backdoor attacks. Our methods are (1) powerful: our triggers can both promote the two phases (i.e., the backdoor implantation and activation phase) in backdoor attacks simultaneously; (2) stealthy: our triggers are generated from each image. They are image-specific instead of fixed triggers. Extensive experiments demonstrate that our approach can achieve a fantastic attack success rate~(98.98%) with low poisoning rate~(5%), high stealthiness under many evaluation metrics and is resistant to backdoor defense methods.
Code (0)
등록된 구현이 없습니다.
Tasks
Backdoor Attackbackdoor defenseVocal Bursts Valence PredictionSimilar Papers 제목 키워드 기반
Clean-image Backdoor Attacks
To gather a significant quantity of annotated training data for high-performance image classification models, numerous companies opt to enlist third-party providers to label their unlabeled data. This practice is widely …
Fairnessimage-classificationImage ClassificationModel-agnostic clean-label backdoor mitigation in cybersecurity environments
The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed fo…
backdoor defenseClassificationMalware ClassificationDMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks
Recent studies have revealed that GNNs are highly susceptible to multiple adversarial attacks. Among these, graph backdoor attacks pose one of the most prominent threats, where attackers cause models to misclassify by le…
counterfactualCounterfactual ExplanationA Semantic and Clean-label Backdoor Attack against Graph Convolutional Networks
Graph Convolutional Networks (GCNs) have shown excellent performance in graph-structured tasks such as node classification and graph classification. However, recent research has shown that GCNs are vulnerable to a new ty…
Backdoor AttackGraph ClassificationNode ClassificationLow-Loss Subspace Compression for Clean Gains against Multi-Agent Backdoor Attacks
Recent exploration of the multi-agent backdoor attack demonstrated the backfiring effect, a natural defense against backdoor attacks where backdoored inputs are randomly classified. This yields a side-effect of low accur…
Backdoor Attack