Efficient Black-Box Adversarial Attacks on Neural Text Detectors
Neural text detectors are models trained to detect whether a given text was generated by a language model or written by a human. In this paper, we investigate three simple and resource-efficient strategies (parameter tweaking, prompt engineering, and character-level mutations) to alter texts generated by GPT-3.5 that are unsuspicious or unnoticeable for humans but cause misclassification by neural text detectors. The results show that especially parameter tweaking and character-level mutations are effective strategies.
Code (1)
Tasks
Language ModelingLanguage ModellingPrompt EngineeringMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Context-Aware Transfer Attacks for Object Detection
Blackbox transfer attacks for image classifiers have been extensively studied in recent years. In contrast, little progress has been made on transfer attacks for object detectors. Object detectors take a holistic view of…
Objectobject-detectionObject DetectionMulti-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid
While extensive research exists on physical adversarial attacks within the visible spectrum, studies on such techniques in the infrared spectrum are limited. Infrared object detectors are vital in modern technological ap…
Log-normal Mutations and their Use in Detecting Surreptitious Fake Images
In many cases, adversarial attacks are based on specialized algorithms specifically dedicated to attacking automatic image classifiers. These algorithms perform well, thanks to an excellent ad hoc distribution of initial…
Zero-Query Transfer Attacks on Context-Aware Object Detectors
Adversarial attacks perturb images such that a deep neural network produces incorrect classification results. A promising approach to defend against adversarial attacks on natural multi-object scenes is to impose a conte…
Adversarial AttackObjectOut-of-the-box: Black-box Causal Attacks on Object Detectors
Adversarial perturbations are a useful way to expose vulnerabilities in object detectors. Existing perturbation methods are frequently white-box, architecture specific and use a loss function. More importantly, while the…