相关论文: Complete Evasion, Zero Modification: PDF Attacks o…

We propose an accurate and efficient scene text detection framework, termed FAST (i.e., faster arbitrarily-shaped text detector). Different from recent advanced text detectors that used complicated post-processing and hand-crafted network…

The rapid adoption of generative AI tools has heightened concerns regarding academic integrity, as students increasingly engage in dishonest practices by copying or paraphrasing AI-generated content. Existing plagiarism detection systems,…

The number of published PDF documents has increased exponentially in recent decades. There is a growing need to make their rich content discoverable to information retrieval tools. In this paper, we present a novel approach to document…

Program fuzzing---providing randomly constructed inputs to a computer program---has proved to be a powerful way to uncover bugs, find security vulnerabilities, and generate test inputs that increase code coverage. In many applications,…

While AI-coding assistants accelerate software development, current testing frameworks struggle to keep pace with the resulting volume of AI-generated code. Traditional fuzzing techniques often allocate resources uniformly and lack semantic…

Many word-level adversarial attack approaches for textual data have been proposed in recent studies. However, due to the massive search space consisting of combinations of candidate words, the existing approaches face the problem of…

MLFuzz, a work accepted at ACM FSE 2023, revisits the performance of a machine learning-based fuzzer, NEUZZ. We demonstrate that its main conclusion is entirely wrong due to several fatal bugs in the implementation and wrong evaluation…

The recent large language models (LLMs), e.g., ChatGPT, have been able to generate human-like and fluent responses when provided with specific instructions. While admitting the convenience brought by technological advancement, educators…

The automatic scoring of summaries is important as it guides the development of summarizers. Scoring is also complex, as it involves multiple aspects such as fluency, grammar, and even textual entailment with the source text. However,…

Social media platforms are plagued by harmful content such as hate speech, misinformation, and extremist rhetoric. Machine learning (ML) models are widely adopted to detect such content; however, they remain highly vulnerable to adversarial…

In recent years, traditional cybersecurity safeguards have proven ineffective against insider threats. Famous cases of sensitive information leaks caused by insiders, including the WikiLeaks release of diplomatic cables and the Edward…

To pursue comprehensive performance, recent text detectors improve detection speed at the expense of accuracy. They adopt shrink-mask based text representation strategies, which leads to a high dependency of detection accuracy on…

Widely applied large language models (LLMs) can generate human-like content, raising concerns about the abuse of LLMs. Therefore, it is important to build strong AI-generated text (AIGT) detectors. Current works only consider document-level…

Visual Document Understanding (VDU) systems have achieved strong performance in information extraction by integrating textual, layout, and visual signals. However, their robustness under realistic adversarial perturbations remains…

In recent years, coverage-based greybox fuzzing has proven itself to be one of the most effective techniques for finding security bugs in practice. Particularly, American Fuzzy Lop (AFL for short) is deemed to be a great success in fuzzing…

In the exciting generative AI era, the diffusion model has emerged as a very powerful and widely adopted content generation and editing tool for various data modalities, making the study of their potential security risks very necessary and…

Large Language Models (LLMs) have transformed human-machine interaction since ChatGPT's 2022 debut, with Retrieval-Augmented Generation (RAG) emerging as a key framework that enhances LLM outputs by integrating external knowledge. However,…

Recent advances in text-based image editing have enabled fine-grained manipulation of visual content guided by natural language. However, such methods are susceptible to adversarial attacks. In this work, we propose a novel attack that…

With the ongoing popularization of online services, the digital document images have been used in various applications. Meanwhile, there have emerged some deep learning-based text editing algorithms which alter the textual information of an…

Many commercial and open-source models claim to detect machine-generated text with extremely high accuracy (99% or more). However, very few of these detectors are evaluated on shared benchmark datasets and even when they are, the datasets…