Related papers: Semantic-level Backdoor Attack against Text-to-Ima…

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Interpretability is crucial to understand the inner workings of deep neural networks (DNNs) and many interpretation methods generate saliency maps that highlight parts of the input image that contribute the most to the prediction made by…

Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The backdoor-compromised model will mis-classify to the target…

Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while…

Modern language models remain vulnerable to backdoor attacks via poisoned data, where training inputs containing a trigger are paired with a target output, causing the model to reproduce that behavior whenever the trigger appears at…

Multimodal pretrained models are vulnerable to backdoor attacks, yet most existing methods rely on visual or multimodal triggers, which are impractical since visually embedded triggers rarely occur in real-world data. To overcome this…

Spiking Neural Networks (SNNs) have gained increasing attention for their superior energy efficiency compared to Artificial Neural Networks (ANNs). However, their security aspects, particularly under backdoor attacks, have received limited…

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and formalize the inscriptive jailbreak, where an adversary coerces a T2I system into generating…

Large Vision-Language Models (LVLMs) are susceptible to typographic attacks, which are misclassifications caused by an attack text that is added to an image. In this paper, we introduce a multi-image setting for studying typographic…

Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which…

Semantic communications seeks to transfer information from a source while conveying a desired meaning to its destination. We model the transmitter-receiver functionalities as an autoencoder followed by a task classifier that evaluates the…

Large-scale language models have achieved tremendous success across various natural language processing (NLP) applications. Nevertheless, language models are vulnerable to backdoor attacks, which inject stealthy triggers into models for…

Deep neural network-based image classifications are vulnerable to adversarial perturbations. The image classifications can be easily fooled by adding artificial small and imperceptible perturbations to input images. As one of the most…

With the widespread application of deep learning across various domains, concerns about its security have grown significantly. Among these, backdoor attacks pose a serious security threat to deep neural networks (DNNs). In recent years,…

Semantic communication enhances transmission efficiency by conveying semantic information rather than raw input symbol sequences. Task-oriented semantic communication is a variant that tries to retains only task-specific information, thus…

Backdoor attacks on federated learning (FL) are most often evaluated with synthetic corner patches or out-of-distribution (OOD) patterns that are unlikely to arise in practice. In this paper, we revisit the backdoor threat to standard FL (a…

Text-to-image (T2I) models have been widely applied in generating high-fidelity images across various domains. However, these models may also be abused to produce Not-Safe-for-Work (NSFW) content via jailbreak attacks. Existing jailbreak…

In recent years there has been enormous interest in vision-language models trained using self-supervised objectives. However, the use of large-scale datasets scraped from the web for training also makes these models vulnerable to potential…

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…