Defending Backdoor Data Poisoning Attacks by Using Noisy Label Defense Algorithm
Training deep neural networks with data corruption is a challenging problem. One example of such corruption is the backdoor data poisoning attack, in which an adversary strategically injects a backdoor trigger to a small fraction of the training data to subtly compromise the training process. Consequently, the trained deep neural network would misclassify testing examples that have been corrupted by the same trigger. While the label of the data could be changed to arbitrary values by an adversary, the extent of corruption injected to the feature values are strictly limited in order to keep the backdoor attack in disguise, which leads to a resemblance between the backdoor attack and a milder attack that involves only noisy labels. In this paper, we investigate an intriguing question: Can we leverage algorithms that defend against noisy labels corruptions to defend against general backdoor attacks? We first discuss the limitations of directly using the noisy-label defense algorithms to defend against backdoor attacks. Next, we propose a meta-algorithm that transforms an existing noisy label defense algorithm to one that protects against backdoor attacks. Extensive experiments on different types of backdoor attacks show that, by introducing a lightweight alteration for minimax optimization to the existing noisy-label defense algorithms, the robustness against backdoor attacks can be substantially improved, while the intial form of those algorithms would fail in presence of a backdoor attacks.
Code (0)
등록된 구현이 없습니다.
Tasks
Backdoor AttackData PoisoningSimilar Papers 제목 키워드 기반
Defending Against Weight-Poisoning Backdoor Attacks for Parameter-Efficient Fine-Tuning
Recently, various parameter-efficient fine-tuning (PEFT) strategies for application to language models have been proposed and successfully implemented. However, this raises the question of whether PEFT, which only update…
Backdoor Attackparameter-efficient fine-tuningtext-classificationText ClassificationSemantic Shield: Defending Vision-Language Models Against Backdooring and Poisoning via Fine-grained Knowledge Alignment
In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vuln…
Language ModelingLanguage ModellingDefending against Insertion-based Textual Backdoor Attacks via Attribution
Textual backdoor attack, as a novel attack model, has been shown to be effective in adding a backdoor to the model during training. Defending against such backdoor attacks has become urgent and important. In this paper, …
Backdoor AttackLanguage ModelingLanguage ModellingDetecting Backdoors in Deep Text Classifiers
Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attach…
Data Poisoningtext-classificationText ClassificationBetter Safe than Sorry: Pre-training CLIP against Targeted Data Poisoning and Backdoor Attacks
Contrastive Language-Image Pre-training (CLIP) on large image-caption datasets has achieved remarkable success in zero-shot classification and enabled transferability to new domains. However, CLIP is extremely more vulne…
Contrastive LearningData Poisoningzero-shot-classificationZero-Shot Learning