Related papers: Localization then Neutralization: Gradient-guided …

Textual adversarial examples pose serious threats to the reliability of natural language processing systems. Recent studies suggest that adversarial examples tend to deviate from the underlying manifold of normal texts, whereas pre-trained…

Prompt injection attacks pose a significant challenge to the safe deployment of Large Language Models (LLMs) in real-world applications. While prompt-based detection offers a lightweight and interpretable defense strategy, its effectiveness…

While pre-trained Transformer models achieve high accuracy on in-domain sentiment classification, they frequently experience severe performance degradation when transferring to out-of-domain data. We hypothesize that this generalization gap…

Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them together into a single stream of text. However, the LLM is…

Augmenting language models with image inputs may enable more effective jailbreak attacks through continuous optimization, unlike text inputs that require discrete optimization. However, new multimodal fusion models tokenize all input…

Keyless entry systems in cars are adopting neural networks for localizing its operators. Using test-time adversarial defences equip such systems with the ability to defend against adversarial attacks without prior training on adversarial…

In recent years, machine learning algorithms have been applied widely in various fields such as health, transportation, and the autonomous car. With the rapid developments of deep learning techniques, it is critical to take the security…

Deep neural networks are known to be vulnerable to adversarial examples crafted by adding human-imperceptible perturbations to the benign input. After achieving nearly 100% attack success rates in white-box setting, more focus is shifted to…

Visual place retrieval aims to search images in the database that depict similar places as the query image. However, global descriptors encoded by the network usually fall into a low dimensional principal space, which is harmful to the…

The nature of deep neural networks has given rise to a variety of attacks, but little work has been done to address the effect of adversarial attacks on segmentation models trained on MRI datasets. In light of the grave consequences that…

Numerous recent studies have demonstrated how Deep Neural Network (DNN) classifiers can be fooled by adversarial examples, in which an attacker adds perturbations to an original sample, causing the classifier to misclassify the sample.…

In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent…

The reliance on deep learning algorithms has grown significantly in recent years. Yet, these models are highly vulnerable to adversarial attacks, which introduce visually imperceptible perturbations into testing data to induce…

In recent years, Large Language Models (LLM) have emerged as pivotal tools in various applications. However, these models are susceptible to adversarial prompt attacks, where attackers can carefully curate input strings that mislead LLMs…

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Adversarial text attacks remain a persistent threat to transformer models, yet existing defenses are typically attack-specific or require costly model retraining, leaving a gap for attack-agnostic detection. We introduce Guided Perturbation…

Neural networks are trained primarily based on their inputs and outputs, without regard for their internal mechanisms. These neglected mechanisms determine properties that are critical for safety, like (i) transparency; (ii) the absence of…

The notion of adversarial attacks on image classification models based on convolutional neural networks (CNN) is introduced in this work. To classify images, deep learning models called CNNs are frequently used. However, when the networks…

Although multimodal large language models (MLLMs) are increasingly deployed in real-world applications, their instruction-following behavior leaves them vulnerable to prompt injection attacks. Existing prompt injection methods predominantly…

Prompt learning has achieved great success in efficiently exploiting large-scale pre-trained models in natural language processing (NLP). It reformulates the downstream tasks as the generative pre-training ones to achieve consistency, thus…