相关论文: Efficient Black-Box Adversarial Attacks on Neural …

Large Language Models (LLMs) are gearing up to surpass human creativity. The veracity of the statement needs careful consideration. In recent developments, critical questions arise regarding the authenticity of human work and the…

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

Visual modifications to text are often used to obfuscate offensive comments in social media (e.g., "!d10t") or as a writing style ("1337" in "leet speak"), among other scenarios. We consider this as a new type of adversarial attack in NLP,…

Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3.5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive.…

Deep neural networks (DNNs) are vulnerable to adversarial examples, perturbations to correctly classified examples which can cause the model to misclassify. In the image domain, these perturbations are often virtually indistinguishable to…

Large Language Model (LLMs) can be used to write or modify documents, presenting a challenge for understanding the intent behind their use. For example, benign uses may involve using LLM on a human-written document to improve its grammar or…

To combat the potential misuse of Natural Language Generation (NLG) technology, a variety of algorithms have been developed for the detection of AI-generated texts. Traditionally, this task is treated as a binary classification problem.…

In the last decade, deep neural networks have proven to be very powerful in computer vision tasks, starting a revolution in the computer vision and machine learning fields. However, deep neural networks, usually, are not robust to…

Deep neural networks for natural language processing tasks are vulnerable to adversarial input perturbations. In this paper, we present a versatile language for programmatically specifying string transformations -- e.g., insertions,…

In Machine Learning, White Box Adversarial Attacks rely on knowing underlying knowledge about the model attributes. This works focuses on discovering to distrinct pieces of model information: the underlying architecture and primary training…

Textual information in a captured scene plays an important role in scene interpretation and decision making. Though there exist methods that can successfully detect and interpret complex text regions present in a scene, to the best of our…

Large language models (LLMs) have demonstrated remarkable capability to generate fluent responses to a wide variety of user queries. However, this has also raised concerns about the potential misuse of such texts in journalism, education,…

Nowadays, powerful large language models (LLMs) such as ChatGPT have demonstrated revolutionary power in a variety of tasks. Consequently, the detection of machine-generated texts (MGTs) is becoming increasingly crucial as LLMs become more…

The ability of large language models to generate complex texts allows them to be widely integrated into many aspects of life, and their output can quickly fill all network resources. As the impact of LLMs grows, it becomes increasingly…

Training or finetuning large-scale language models (LLMs) such as GPT-3 requires substantial computation resources, motivating recent efforts to explore parameter-efficient adaptation to downstream tasks. One practical area of research is…

NLP models are shown to suffer from robustness issues, i.e., a model's prediction can be easily changed under small perturbations to the input. In this work, we present a Controlled Adversarial Text Generation (CAT-Gen) model that, given an…

Since language models produce fake text quickly and easily, there is an oversupply of such content in the public domain. The degree of sophistication and writing style has reached a point where differentiating between human authored and…

The increasing difficulty to distinguish language-model-generated from human-written text has led to the development of detectors of machine-generated text (MGT). However, in many contexts, a black-box prediction is not sufficient, it is…

We introduce Ghostbuster, a state-of-the-art system for detecting AI-generated text. Our method works by passing documents through a series of weaker language models, running a structured search over possible combinations of their features,…

AI humanizers are a new class of online software tools meant to paraphrase and rewrite AI-generated text in a way that allows them to evade AI detection software. We study 19 AI humanizer and paraphrasing tools and qualitatively assess…