Add to ORKGThe prevalence and strong capability of large language models (LLMs) present significant safety and ethical risks if exploited by malicious users. To prevent the potentially deceptive usage of LLMs, recent works have proposed algorithms to detect LLM-generated text and protect LLMs. In this paper, we investigate the robustness and reliability of these LLM detectors under adversarial attacks. We study two types of attack strategies: 1) replacing certain words in an LLM's output with their synonyms given the context; 2) automatically searching for an instructional prompt to alter the writing style of the generation. In both strategies, we leverage an auxiliary LLM to generate the word replacements or the instructional prompt. Different from p...
As large language models are integrated into society, robustness toward a suite of prompts is increa...
Large language models (LLMs) such as ChatGPT are increasingly being used for various use cases, incl...
Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabil...
Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to genera...
Recent advances in large language models (LLMs) and the intensifying popularity of ChatGPT-like appl...
Recently, Large Language Models (LLMs) have made significant advancements and are now widely used ac...
Spurred by the recent rapid increase in the development and distribution of large language models (L...
Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficu...
Adversarial attacks in NLP challenge the way we look at language models. The goal of this kind of ad...
Large Language Models (LLMs) are artificial intelligence (AI) tools that can process, summarize, and...
With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has r...
Recently, text watermarking algorithms for large language models (LLMs) have been mitigating the pot...
The monumental achievements of deep learning (DL) systems seem to guarantee the absolute superiority...
Adversarial attacks are a major challenge faced by current machine learning research. These purposel...
We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts gener...
As large language models are integrated into society, robustness toward a suite of prompts is increa...
Large language models (LLMs) such as ChatGPT are increasingly being used for various use cases, incl...
Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabil...
Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to genera...
Recent advances in large language models (LLMs) and the intensifying popularity of ChatGPT-like appl...
Recently, Large Language Models (LLMs) have made significant advancements and are now widely used ac...
Spurred by the recent rapid increase in the development and distribution of large language models (L...
Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficu...
Adversarial attacks in NLP challenge the way we look at language models. The goal of this kind of ad...
Large Language Models (LLMs) are artificial intelligence (AI) tools that can process, summarize, and...
With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has r...
Recently, text watermarking algorithms for large language models (LLMs) have been mitigating the pot...
The monumental achievements of deep learning (DL) systems seem to guarantee the absolute superiority...
Adversarial attacks are a major challenge faced by current machine learning research. These purposel...
We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts gener...
As large language models are integrated into society, robustness toward a suite of prompts is increa...
Large language models (LLMs) such as ChatGPT are increasingly being used for various use cases, incl...
Larger language models (LLMs) have taken the world by storm with their massive multi-tasking capabil...