Related papers: MASH: Evading Black-Box AI-Generated Text Detector…
Recent studies have demonstrated the vulnerability of Automatic Speech Recognition systems to adversarial examples, which can deceive these systems into misinterpreting input speech commands. While previous research has primarily focused on…
In recent years, there has been a rapid proliferation of AI-generated text, primarily driven by the release of powerful pre-trained language models (PLMs). To address the issue of misuse associated with AI-generated text, various…
Language generation models' democratization benefits many domains, from answering health-related questions to enhancing education by providing AI-driven tutoring services. However, language generation models' democratization also makes it…
Machine Learning (ML)-based malicious traffic detection is a promising security paradigm. It outperforms rule-based traditional detection by identifying various advanced attacks. However, the robustness of these ML models is largely…
The powerful ability to understand, follow, and generate complex language emerging from large language models (LLMs) makes LLM-generated text flood many areas of our daily lives at an incredible speed and is widely accepted by humans. As…
Technology for open-ended language generation, a key application of artificial intelligence, has advanced to a great extent in recent years. Large-scale language models, which are trained on large corpora of text, are being used in a wide…
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…
Adversarial attacks remain a significant threat that can jeopardize the integrity of Machine Learning (ML) models. In particular, query-based black-box attacks can generate malicious noise without having access to the victim model's…
Detecting AI-generated text is an important but challenging problem. Existing likelihood-based detection methods are often sensitive to content complexity and may exhibit unstable performance. In this paper, our key insight is that modern…
We present Azimuth, an open-source and easy-to-use tool to perform error analysis for text classification. Compared to other stages of the ML development cycle, such as model training and hyper-parameter tuning, the process and tooling for…
Large language models (LLMs) have shown the capability to generate fluent and logical content, presenting significant challenges to machine-generated text detection, particularly text polished by adversarial perturbations such as…
The misuse of large language models (LLMs) poses potential risks, motivating the development of machine-generated text (MGT) detection. Existing literature primarily concentrates on binary, document-level detection, thereby neglecting texts…
Recent advancements in machine learning have spurred growing interests in automated interpreting quality assessment. Nevertheless, existing research suffers from insufficient examination of language use quality, unsatisfactory modeling…
Domain generation algorithms (DGAs) are commonly used by botnets to generate domain names through which bots can establish a resilient communication channel with their command and control servers. Recent publications presented deep…
Recent advances in large language models (LLMs) have blurred the boundary of high-quality text generation between humans and machines, which is favorable for generative text steganography. While, current advanced steganographic mapping is…
Numerous methods for crafting adversarial examples were proposed recently with high success rate. Since most existing machine learning based classifiers normalize images into some continuous, real vector, domain firstly, attacks often craft…
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…
Neural text ranking models have witnessed significant advancement and are increasingly being deployed in practice. Unfortunately, they also inherit adversarial vulnerabilities of general neural models, which have been detected but remain…
In recent years, Cross-Modal Hashing (CMH) has aroused much attention due to its fast query speed and efficient storage. Previous literatures have achieved promising results for Cross-Modal Retrieval (CMR) by discovering discriminative hash…
The increasing sophistication of AI-generated texts highlights the urgent need for accurate and transparent detection tools, especially in educational settings, where verifying authorship is essential. Existing literature has demonstrated…