Related papers: RADAR: Run-time Adversarial Weight Attack Detectio…
Radio frequency fingerprint identification (RFFI) is an emerging technique for the lightweight authentication of wireless Internet of things (IoT) devices. RFFI exploits deep learning models to extract hardware impairments to uniquely…
As designers of artificial intelligence try to outwit hackers, both sides continue to hone in on AI's inherent vulnerabilities. Designed and trained from certain statistical distributions of data, AI's deep neural networks (DNNs) remain…
The combination of deep unfolding with vector approximate message passing (VAMP) algorithm, results in faster convergence and higher sparse recovery accuracy than traditional compressive sensing approaches. However, deep unfolding alters…
Synthetic aperture radar (SAR) imagery exhibits intrinsic information sparsity due to its unique electromagnetic scattering mechanism. Despite the widespread adoption of deep neural network (DNN)-based SAR automatic target recognition…
Backdoor attacks pose severe security threats to deep neural networks by embedding malicious triggers that force misclassification. While machine unlearning techniques can remove backdoor behaviors, current methods lack transparency and…
Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well on the validation dataset designed for the task, but a small…
In recent years Deep Neural Networks (DNNs) have achieved remarkable results and even showed super-human capabilities in a broad range of domains. This led people to trust in DNNs' classifications and resulting actions even in…
Adversarial attacks pose a critical security threat to real-world AI systems by injecting human-imperceptible perturbations into benign samples to induce misclassification in deep learning models. While existing detection methods, such as…
Resistive random-access memory (ReRAM)-based processing-in-memory (PIM) architecture is an attractive solution for training Graph Neural Networks (GNNs) on edge platforms. However, the immature fabrication process and limited write…
Neural networks are vulnerable to adversarial attacks -- small visually imperceptible crafted noise which when added to the input drastically changes the output. The most effective method of defending against these adversarial attacks is to…
While deep neural networks have excellent results in many fields, they are susceptible to interference from attacking samples resulting in erroneous judgments. Feature-level attacks are one of the effective attack types, which targets the…
Modern deep neural networks(DNNs) are vulnerable to adversarial samples. Sparse adversarial samples are a special branch of adversarial samples that can fool the target model by only perturbing a few pixels. The existence of the sparse…
Recent advances in machine learning show that neural models are vulnerable to minimally perturbed inputs, or adversarial examples. Adversarial algorithms are optimization problems that minimize the accuracy of ML models by perturbing…
In practice, deep neural networks have been found to be vulnerable to various types of noise, such as adversarial examples and corruption. Various adversarial defense methods have accordingly been developed to improve adversarial robustness…
This paper examines the vulnerabilities of convolutional neural networks (CNNs) to adversarial attacks and explores a method for their safeguarding. In this study, CNNs were implemented on four of the most common image datasets, namely…
One major goal of the AI security community is to securely and reliably produce and deploy deep learning models for real-world applications. To this end, data poisoning based backdoor attacks on deep neural networks (DNNs) in the production…
Despite demonstrating superior rate-distortion (RD) performance, learning-based image compression (LIC) algorithms have been found to be vulnerable to malicious perturbations in recent studies. However, the adversarial attacks considered in…
The RRAM-based neuromorphic computing system has amassed explosive interests for its superior data processing capability and energy efficiency than traditional architectures, and thus being widely used in many data-centric applications. The…
Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations. Although adversarial training (AT) has proven to be an effective defense approach, we find that the AT-trained models heavily rely on…
We identify fragile and robust neurons of deep learning architectures using nodal dropouts of the first convolutional layer. Using an adversarial targeting algorithm, we correlate these neurons with the distribution of adversarial attacks…