English
Related papers

Related papers: Complete Evasion, Zero Modification: PDF Attacks o…

200 papers

While large language models (LLMs) exhibit significant utility across various domains, they simultaneously are susceptible to exploitation for unethical purposes, including academic misconduct and dissemination of misinformation.…

Computation and Language · Computer Science 2024-09-24 Navid Ayoobi , Lily Knab , Wen Cheng , David Pantoja , Hamidreza Alikhani , Sylvain Flamant , Jin Kim , Arjun Mukherjee

The growing popularity of large language models has raised concerns regarding the potential to misuse AI-generated text (AIGT). It becomes increasingly critical to establish an excellent AIGT detection method with high generalization and…

Computation and Language · Computer Science 2025-07-28 Yinghan Zhou , Juan Wen , Wanli Peng , Yiming Xue , Ziwei Zhang , Zhengxian Wu

ChatGPT brings revolutionary social value but also raises concerns about the misuse of AI-generated text. Consequently, an important question is how to detect whether texts are generated by ChatGPT or by human. Existing detectors are built…

Computation and Language · Computer Science 2023-10-16 Shuyang Cai , Wanyun Cui

Text-to-image diffusion models have been widely adopted in real-world applications due to their ability to generate realistic images from textual descriptions. However, recent studies have shown that these methods are vulnerable to backdoor…

Computer Vision and Pattern Recognition · Computer Science 2024-08-29 Oscar Chew , Po-Yi Lu , Jayden Lin , Hsuan-Tien Lin

Malicious PDF files have emerged as a persistent threat and become a popular attack vector in web-based attacks. While machine learning-based PDF malware classifiers have shown promise, these classifiers are often susceptible to adversarial…

Cryptography and Security · Computer Science 2025-12-08 Side Liu , Jiang Ming , Guodong Zhou , Xinyi Liu , Jianming Fu , Guojun Peng

At present, multi-oriented text detection methods based on deep neural network have achieved promising performances on various benchmarks. Nevertheless, there are still some difficulties for arbitrary shape text detection, especially for a…

Computer Vision and Pattern Recognition · Computer Science 2020-04-17 XiaoQian Li , Jie Liu , ShuWu Zhang , GuiXuan Zhang

The potentials of Generative-AI technologies like Large Language models (LLMs) to revolutionize education are undermined by ethical considerations around their misuse which worsens the problem of academic dishonesty. LLMs like GPT-4 and…

Machine Learning · Computer Science 2024-07-11 Suriya Prakash Jambunathan , Ashwath Shankarnarayan , Parijat Dube

This paper introduces AIDetx, a novel method for detecting machine-generated text using data compression techniques. Traditional approaches, such as deep learning classifiers, often suffer from high computational costs and limited…

Computation and Language · Computer Science 2024-12-02 Leonardo Almeida , Pedro Rodrigues , Diogo Magalhães , Armando J. Pinho , Diogo Pratas

Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficult to distinguish between human-written and LLM-generated texts. This poses a growing risk of misuse of LLMs and demands the development of…

Computation and Language · Computer Science 2024-02-20 Ryuto Koike , Masahiro Kaneko , Naoaki Okazaki

In this work we find that many current redactions of PDF text are insecure due to non-redacted character positioning information. In particular, subpixel-sized horizontal shifts in redacted and non-redacted characters can be recovered and…

Cryptography and Security · Computer Science 2025-10-02 Maxwell Bland , Anushya Iyer , Kirill Levchenko

Evasion techniques allow malicious code to never be observed. This impacts significantly the detection capabilities of tools that rely on either dynamic or static analysis, as they never get to process the malicious code. The dynamic nature…

Cryptography and Security · Computer Science 2024-05-24 Nikolaos Pantelaios , Alexandros Kapravelos

Recent proposals advocate using keystroke timing signals, specifically the coefficient of variation ($\delta$) of inter-keystroke intervals, to distinguish human-composed text from AI-generated content. We demonstrate that this class of…

Cryptography and Security · Computer Science 2026-01-27 David Condrey

AI-text detectors face a critical robustness challenge: adversarial paraphrasing attacks that preserve semantics while evading detection. We introduce StealthRL, a reinforcement learning framework that stress-tests detector robustness under…

Machine Learning · Computer Science 2026-03-23 Suraj Ranganath , Atharv Ramesh

This paper introduces EXaCTz, a parallel algorithm that concurrently preserves extremum graphs and contour trees in lossy-compressed scalar field data. While error-bounded lossy compression is essential for large-scale scientific…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-04-03 Yuxiao Li , Mingze Xia , Xin Liang , Bei Wang , Hanqi Guo

As large language models (LLMs) become increasingly commonplace, concern about distinguishing between human and AI text increases as well. The growing power of these models is of particular concern to teachers, who may worry that students…

Artificial Intelligence · Computer Science 2024-04-18 James Weichert , Chinecherem Dimobi

We present DOCFORGE-BENCH, the first unified zero-shot benchmark for document forgery detection, evaluating 14 methods across eight datasets spanning text tampering, receipt forgery, and identity document manipulation. Unlike…

Computer Vision and Pattern Recognition · Computer Science 2026-03-11 Zengqi Zhao , Weidi Xia , En Wei , Yan Zhang , Jane Mo , Tiannan Zhang , Yuanqin Dai , Zexi Chen , Yiran Tao , Simiao Ren

A fuzzer provides randomly generated inputs to a targeted software to expose erroneous behavior. To efficiently detect defects, generated inputs should conform to the structure of the input format and thus, grammars can be used to generate…

Software Engineering · Computer Science 2020-08-05 Martin Eberlein , Yannic Noller , Thomas Vogel , Lars Grunske

The success of a fuzzing campaign is heavily depending on the quality of seed inputs used for test generation. It is however challenging to compose a corpus of seed inputs that enable high code and behavior coverage of the target program,…

Cryptography and Security · Computer Science 2025-09-16 Liang Cheng , Yang Zhang , Yi Zhang , Chen Wu , Zhangtan Li , Yu Fu , Haisheng Li

This work introduces Llamazip, a novel lossless text compression algorithm based on the predictive capabilities of the LLaMA3 language model. Llamazip achieves significant data reduction by only storing tokens that the model fails to…

Machine Learning · Computer Science 2025-11-25 Sören Dréano , Derek Molloy , Noel Murphy

The rapid proliferation of AI-generated text online is profoundly reshaping the information landscape. Among various types of AI-generated text, AI-generated news presents a significant threat as it can be a prominent source of…

Computation and Language · Computer Science 2023-09-07 Tharindu Kumarage , Amrita Bhattacharjee , Djordje Padejski , Kristy Roschke , Dan Gillmor , Scott Ruston , Huan Liu , Joshua Garland