相关论文: Identifying Adversarial Sentences by Analyzing Tex…

The rapid advancement of Large Language Models (LLMs) has ushered in an era where AI-generated text is increasingly indistinguishable from human-generated content. Detecting AI-generated text has become imperative to combat misinformation,…

Large Language Models (LLMs) can generate highly persuasive text, raising concerns about their misuse for propaganda, manipulation, and other harmful purposes. This leads us to our central question: Is LLM-generated persuasion more…

The author-specific word usage is a vital feature to let readers perceive the writing style of the author. In this work, a personalized sentence generation method based on generative adversarial networks (GANs) is proposed to cope with this…

Adversarial examples are inputs to a machine learning system that result in an incorrect output from that system. Attacks launched through this type of input can cause severe consequences: for example, in the field of image recognition, a…

Adversarial sample attacks perturb benign inputs to induce DNN misbehaviors. Recent research has demonstrated the widespread presence and the devastating consequences of such attacks. Existing defense techniques either assume prior…

As advanced modern systems like deep neural networks (DNNs) and generative AI continue to enhance their capabilities in producing convincing and realistic content, the need to distinguish between user-generated and machine generated content…

Adversarial machine learning is a fast growing research area, which considers the scenarios when machine learning systems may face potential adversarial attackers, who intentionally synthesize input data to make a well-trained model to make…

In text classification, creating an adversarial example means subtly perturbing a few words in a sentence without changing its meaning, causing it to be misclassified by a classifier. A concerning observation is that a significant portion…

Adversarial evaluation stress tests a model's understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose human-in-the-loop…

Written language contains stylistic cues that can be exploited to automatically infer a variety of potentially sensitive author information. Adversarial stylometry intends to attack such models by rewriting an author's text. Our research…

My research investigates the use of cutting-edge hybrid deep learning models to accurately differentiate between AI-generated text and human writing. I applied a robust methodology, utilising a carefully selected dataset comprising AI and…

Recent advances in generative pre-trained transformer large language models have emphasised the potential risks of unfair use of artificial intelligence (AI) generated content in an academic environment and intensified efforts in searching…

Artificial intelligence is known as the most effective technological field for rapid developments shaping the future of the world. Even today, it is possible to see intense use of intelligence systems in all fields of the life. Although…

Recent studies have shown that state-of-the-art deep learning models are vulnerable to the inputs with small perturbations (adversarial examples). We observe two critical obstacles in adversarial examples: (i) Strong adversarial attacks…

Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based…

Current neural-network-based classifiers are susceptible to adversarial examples. The most empirically successful approach to defending against such adversarial examples is adversarial training, which incorporates a strong self-attack…

Nowadays, the usage of Large Language Models (LLMs) has increased, and LLMs have been used to generate texts in different languages and for different tasks. Additionally, due to the participation of remarkable companies such as Google and…

Compromised accounts on social networks are regular user accounts that have been taken over by an entity with malicious intent. Since the adversary exploits the already established trust of a compromised account, it is crucial to detect…

Online users today are exposed to misleading and propagandistic news articles and media posts on a daily basis. To counter thus, a number of approaches have been designed aiming to achieve a healthier and safer online news and media…

Following great success in the image processing field, the idea of adversarial training has been applied to tasks in the natural language processing (NLP) field. One promising approach directly applies adversarial training developed in the…