Kallima: A Clean-label Framework for Textual Backdoor Attacks
Although Deep Neural Network (DNN) has led to unprecedented progress in various natural language processing (NLP) tasks, research shows that deep models are extremely vulnerable to backdoor attacks. The existing backdoor attacks mainly inject a small number of poisoned samples into the training dataset with the labels changed to the target one. Such mislabeled samples would raise suspicion upon human inspection, potentially revealing the attack. To improve the stealthiness of textual backdoor attacks, we propose the first clean-label framework Kallima for synthesizing mimesis-style backdoor samples to develop insidious textual backdoor attacks. We modify inputs belonging to the target class with adversarial perturbations, making the model rely more on the backdoor trigger. Our framework is compatible with most existing backdoor triggers. The experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Textual Backdoor Attacks Can Be More Harmful via Two Simple Tricks
Backdoor attacks are a kind of emergent security threat in deep learning. After injected into a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the inpu…
Vocal Bursts Valence PredictionTextual Backdoor Attacks Can Be More Harmful via Two Simple Tricks
Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once th…
Vocal Bursts Valence PredictionPrompt as Triggers for Backdoor Attack: Examining the Vulnerability in Language Models
The prompt-based learning paradigm, which bridges the gap between pre-training and fine-tuning, achieves state-of-the-art performance on several NLP tasks, particularly in few-shot settings. Despite being widely applied,…
Backdoor AttackFew-Shot Text Classificationtext-classificationText ClassificationLarge Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifiers
Backdoor attacks manipulate model predictions by inserting innocuous triggers into training and test data. We focus on more realistic and more challenging clean-label attacks where the adversarial training examples are c…
Triggerless Backdoor Attack for NLP Tasks with Clean Labels
Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a targ…
Backdoor AttackSentence