Attacking interpretable NLP systems
Studies have shown that machine learning systems are vulnerable to adversarial examples in theory and practice. Where previous attacks have focused mainly on visual models that exploit the difference between human and machine perception, text-based models have also fallen victim to these attacks. However, these attacks often fail to maintain the semantic meaning of the text and similarity. This paper introduces AdvChar, a black-box attack on Interpretable Natural Language Processing Systems, designed to mislead the classifier while keeping the interpretation similar to benign inputs, thus exploiting trust in system transparency. AdvChar achieves this by making less noticeable modifications to text input, forcing the deep learning classifier to make incorrect predictions and preserve the original interpretation. We use an interpretation-focused scoring approach to determine the most critical tokens that, when changed, can cause the classifier to misclassify the input. We apply simple character-level modifications to measure the importance of tokens, minimizing the difference between the original and new text while generating adversarial interpretations similar to benign ones. We thoroughly evaluated AdvChar by testing it against seven NLP models and three interpretation models using benchmark datasets for the classification task. Our experiments show that AdvChar can significantly reduce the prediction accuracy of current deep learning models by altering just two characters on average in input samples.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection
Social networks are frequently polluted by rumors, which can be detected by advanced models such as graph neural networks. However, the models are vulnerable to attacks and understanding the vulnerabilities is critical t…
reinforcement-learningReinforcement Learning (RL)What Models Know About Their Attackers: Deriving Attacker Information From Latent Representations
Adversarial attacks curated against NLP models are increasingly becoming practical threats. Although various methods have been developed to detect adversarial attacks, securing learning-based NLP systems in practice woul…
Abuse DetectionAdversarial TextAttributeSentiment Analysis+1Rethinking Targeted Adversarial Attacks For Neural Machine Translation
Targeted adversarial attacks are widely used to evaluate the robustness of neural machine translation systems. Unfortunately, this paper first identifies a critical issue in the existing settings of NMT targeted adversar…
Adversarial AttackMachine TranslationNMTTranslationCheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
Recently, Large Language Model (LLM)-empowered recommender systems (RecSys) have brought significant advances in personalized user experience and have attracted considerable attention. Despite the impressive progress, th…
Large Language ModelRecommendation SystemsReinforcement Learning (RL)Counter-Empirical Attacking based on Adversarial Reinforcement Learning for Time-Relevant Scoring System
Scoring systems are commonly seen for platforms in the era of big data. From credit scoring systems in financial services to membership scores in E-commerce shopping platforms, platform managers use such systems to guide…