Related papers: SemAttack: Natural Textual Attacks via Different S…

We extend BeamAttack, an adversarial attack algorithm designed to evaluate the robustness of text classification systems through word-level modifications guided by beam search. Our extensions include support for word deletions and the…

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on…

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…

Deep neural networks were significantly vulnerable to adversarial examples manipulated by malicious tiny perturbations. Although most conventional adversarial attacks ensured the visual imperceptibility between adversarial examples and…

We proposes a novel algorithm, ANTHRO, that inductively extracts over 600K human-written text perturbations in the wild and leverages them for realistic adversarial attack. Unlike existing character-based attacks which often deductively…

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs,…

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…

We study an important and challenging task of attacking natural language processing models in a hard label black box setting. We propose a decision-based attack strategy that crafts high quality adversarial examples on text classification…

The growing use of social media has led to the development of several Machine Learning (ML) and Natural Language Processing(NLP) tools to process the unprecedented amount of social media content to make actionable decisions. However, these…

Traditional CAPTCHA (Completely Automated Public Turing Test to Tell Computers and Humans Apart) schemes are increasingly vulnerable to automated attacks powered by deep neural networks (DNNs). Existing adversarial attack methods often rely…

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

Recent NLP literature pays little attention to the robustness of toxicity language predictors, while these systems are most likely to be used in adversarial contexts. This paper presents a novel adversarial attack, \texttt{ToxicTrap},…

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving…

This paper presents a framework which enables a user to more easily make corrections to adversarial texts. While attack algorithms have been demonstrated to automatically build adversaries, changes made by the algorithms can often have poor…

Despite outstanding performance in a variety of NLP tasks, recent studies have revealed that NLP models are vulnerable to adversarial attacks that slightly perturb the input to cause the models to misbehave. Among these attacks, adversarial…

Multimodal large language models (MLLMs) have shown impressive capabilities in vision-language tasks such as reasoning segmentation, where models generate segmentation masks based on textual queries. While prior work has primarily focused…

Vision-Language (VL) pre-trained models have shown their superiority on many multimodal tasks. However, the adversarial robustness of such models has not been fully explored. Existing approaches mainly focus on exploring the adversarial…

As large language models become more prevalent, their possible harmful or inappropriate responses are a cause for concern. This paper introduces a unique dataset containing adversarial examples in the form of questions, which we call AttaQ,…

Text-to-image (T2I) diffusion models are widely adopted for their strong generative capabilities, yet remain vulnerable to backdoor attacks. Existing attacks typically rely on fixed textual triggers and single-entity backdoor targets,…

Black-box textual adversarial attacks are challenging due to the lack of model information and the discrete, non-differentiable nature of text. Existing methods often lack versatility for attacking different models, suffer from limited…