相关论文: Adversarial Stylometry in the Wild: Transferable L…

Can language models transform inputs to protect text classifiers against adversarial attacks? In this work, we present ATINTER, a model that intercepts and learns to rewrite adversarial inputs to make them non-adversarial for a downstream…

The growth of highly advanced Large Language Models (LLMs) constitutes a huge dual-use problem, making it necessary to create dependable AI-generated text detection systems. Modern detectors are notoriously vulnerable to adversarial…

Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating…

Despite the remarkable performance and generalization levels of deep learning models in a wide range of artificial intelligence tasks, it has been demonstrated that these models can be easily fooled by the addition of imperceptible yet…

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…

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,…

The increasing capabilities of Large Language Models (LLMs) have raised concerns about their misuse in AI-generated plagiarism and social engineering. While various AI-generated text detectors have been proposed to mitigate these risks,…

Person re-identification (re-id) models are vital in security surveillance systems, requiring transferable adversarial attacks to explore the vulnerabilities of them. Recently, vision-language models (VLM) based attacks have shown superior…

Adversarial examples are maliciously perturbed inputs designed to mislead machine learning (ML) models at test-time. They often transfer: the same adversarial example fools more than one model. In this work, we propose novel methods for…

State-of-the-art deep neural networks are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can \textit{transfer across models}:…

This study investigates the privacy risks associated with text embeddings, focusing on the scenario where attackers cannot access the original embedding model. Contrary to previous research requiring direct model access, we explore a more…

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

Image classification currently faces significant security challenges due to adversarial attacks, which consist of intentional alterations designed to deceive classification models based on artificial intelligence. This article explores an…

Recent studies show that text-to-image (T2I) models are vulnerable to adversarial attacks, especially with noun perturbations in text prompts. In this study, we investigate the impact of adversarial attacks on different POS tags within text…

Deep learning models, while achieving state-of-the-art performance on many tasks, are susceptible to adversarial attacks that exploit inherent vulnerabilities in their architectures. Adversarial attacks manipulate the input data with…

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,…

With Internet users constantly leaving a trail of text, whether through blogs, emails, or social media posts, the ability to write and protest anonymously is being eroded because artificial intelligence, when given a sample of previous…

Transferability of adversarial samples became a serious concern due to their impact on the reliability of machine learning system deployments, as they find their way into many critical applications. Knowing factors that influence…

Various techniques are used in the generation of adversarial examples, including methods such as TextBugger which introduce minor, hardly visible perturbations to words leading to changes in model behaviour. Another class of techniques…

Textual deception constitutes a major problem for online security. Many studies have argued that deceptiveness leaves traces in writing style, which could be detected using text classification techniques. By conducting an extensive…