paper-with-me

홈 › Papers

Efficient Black-Box Adversarial Attacks on Neural Text Detectors

2023-11-03 · Vitalii Fishchuk, Daniel Braun

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.

📄 PDF Abstract BibTeX arXiv:2311.01873

Code (1)

lolya-cloud/adversarial-attacks-on-neural-text-detectors 공식 구현

Tasks

Language ModelingLanguage ModellingPrompt Engineering

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Multi-Head Attention 설명 없음
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Similar Papers 제목 키워드 기반

Context-Aware Transfer Attacks for Object Detection

2021-12-06 · Zikui Cai, Xinxin Xie, Shasha Li, Mingjun Yin 외

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 Detection

Multi-View Black-Box Physical Attacks on Infrared Pedestrian Detectors Using Adversarial Infrared Grid

2024-07-01 · Kalibinuer Tiliwalidi, Chengyin Hu, Weiwen Shi

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

2024-09-23 · Ismail Labiad, Thomas Bäck, Pierre Fernandez, Laurent Najman 외

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

2022-03-29 · CVPR 2022 1 · Zikui Cai, Shantanu Rane, Alejandro E. Brito, Chengyu Song 외

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 AttackObject

Out-of-the-box: Black-box Causal Attacks on Object Detectors

2025-12-03 · Melane Navaratnarajah, David A. Kelly, Hana Chockler arxiv

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…