Related papers: Sampling-based Fast Gradient Rescaling Method for …
Deep neural networks are vulnerable to adversarial examples -- minor perturbations added to a model's input which cause the model to output an incorrect prediction. We introduce a new method for improving the efficacy of adversarial attacks…
One of the most practical and challenging types of black-box adversarial attacks is the hard-label attack, where only the top-1 predicted label is available. One effective approach is to search for the optimal ray direction from the benign…
Spiking Neural Networks (SNNs) as Machine Learning (ML) models have recently received a lot of attention as a potentially more energy-efficient alternative to conventional Artificial Neural Networks. The non-differentiability and sparsity…
Spiking neural networks (SNNs) represent a promising approach in machine learning, combining the hierarchical learning capabilities of deep neural networks with the energy efficiency of spike-based computations. Traditional end-to-end…
Spiking Neural Networks (SNNs) utilize spike-based activations to mimic the brain's energy-efficient information processing. However, the binary and discontinuous nature of spike activations causes vanishing gradients, making adversarial…
Gray-box graph attacks aim at disrupting the performance of the victim model by using inconspicuous attacks with limited knowledge of the victim model. The parameters of the victim model and the labels of the test nodes are invisible to the…
Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are…
Adversarial examples mislead deep neural networks with imperceptible perturbations and have brought significant threats to deep learning. An important aspect is their transferability, which refers to their ability to deceive other models,…
This study investigates the vulnerability of direct data-driven control to adversarial attacks in the form of a small but sophisticated perturbation added to the original data. The directed gradient sign method (DGSM) is developed as a…
Transferable adversarial attacks pose significant threats to deep neural networks, particularly in black-box scenarios where internal model information is inaccessible. Studying adversarial attack methods helps advance the performance of…
Direct Prompt Injection (DPI) attacks pose a critical security threat to Large Language Models (LLMs) due to their low barrier of execution and high potential damage. To address the impracticality of existing white-box/gray-box methods and…
In recent years, there has been a surge in malware attacks across critical infrastructures, requiring further research and development of appropriate response and remediation strategies in malware detection and classification. Several works…
Adversarial generative models, such as Generative Adversarial Networks (GANs), are widely applied for generating various types of data, i.e., images, text, and audio. Accordingly, its promising performance has led to the GAN-based…
Adversarial training is the most successful empirical method for increasing the robustness of neural networks against adversarial attacks. However, the most effective approaches, like training with Projected Gradient Descent (PGD) are…
Transferable attacks generate adversarial examples on surrogate models to fool unknown victim models, posing real-world threats and growing research interest. Despite focusing on flat losses for transferable adversarial examples, recent…
We propose the first general-purpose gradient-based attack against transformer models. Instead of searching for a single adversarial example, we search for a distribution of adversarial examples parameterized by a continuous-valued matrix,…
Deep neural networks are vulnerable to adversarial examples that are crafted by imposing imperceptible changes to the inputs. However, these adversarial examples are most successful in white-box settings where the model and its parameters…
Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughput-limited by the cost of a backward pass. We introduce a…
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.…
The vulnerability of Deep Neural Networks (DNNs) to adversarial examples has been confirmed. Existing adversarial defenses primarily aim at preventing adversarial examples from attacking DNNs successfully, rather than preventing their…