相关论文: SNIFF: Reverse Engineering of Neural Networks with…

Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack. Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very…

Fault injection attacks on embedded neural network models have been shown as a potent threat. Numerous works studied resilience of models from various points of view. As of now, there is no comprehensive study that would evaluate the…

Backdoor attacks represent a serious threat to neural network models. A backdoored model will misclassify the trigger-embedded inputs into an attacker-chosen target label while performing normally on other benign inputs. There are already…

Deep neural networks (DNNs) have made tremendous progress in the past ten years and have been applied in various critical applications. However, recent studies have shown that deep neural networks are vulnerable to backdoor attacks. By…

As autonomous driving and augmented reality evolve, a practical concern is data privacy. In particular, these applications rely on localization based on user images. The widely adopted technology uses local feature descriptors, which are…

Motivated by the transformative impact of deep neural networks (DNNs) in various domains, researchers and anti-virus vendors have proposed DNNs for malware detection from raw bytes that do not require manual feature engineering. In this…

Neural Networks (NNs) are vulnerable to adversarial examples. Such inputs differ only slightly from their benign counterparts yet provoke misclassifications of the attacked NNs. The required perturbations to craft the examples are often…

Deep neural networks (DNNs) excel across image recognition tasks, yet continue to exhibit overconfidence on inputs that bear no resemblance to natural images. Revisiting the "fooling images" work introduced by Nguyen et al. (2015), we…

Security of modern Deep Neural Networks (DNNs) is under severe scrutiny as the deployment of these models become widespread in many intelligence-based applications. Most recently, DNNs are attacked through Trojan which can effectively…

The advancements of deep neural networks (DNNs) have led to their deployment in diverse settings, including safety and security-critical applications. As a result, the characteristics of these models have become sensitive intellectual…

Noisy quantum computers suffer from readout or measurement error. It is a classical bit-flip error due to which state "1" is read out as "0" and vice-versa. The probability of readout error shows a state dependence i.e., flipping…

Fault injection attacks can cause errors in software for malicious purposes. Oftentimes, vulnerable points of a program are detected after its development. It is therefore critical for the user of the program to be able to apply last-minute…

Neural network models implemented in embedded devices have been shown to be susceptible to side-channel attacks (SCAs), allowing recovery of proprietary model parameters, such as weights and biases. There are already available…

The functionality of electronic circuits can be seriously impaired by the occurrence of dynamic hardware faults. Particularly, for digital ultra low-power systems, a reduced safety margin can increase the probability of dynamic failures.…

In adversarial attacks to machine-learning classifiers, small perturbations are added to input that is correctly classified. The perturbations yield adversarial examples, which are virtually indistinguishable from the unperturbed input, and…

We propose a novel deep network structure called "Network In Network" (NIN) to enhance model discriminability for local patches within the receptive field. The conventional convolutional layer uses linear filters followed by a nonlinear…

In this paper, we study the inference accuracy of the Resistive Random Access Memory (ReRAM) neuromorphic circuit due to stuck-at faults (stuck-on, stuck-off, and stuck at a certain resistive value). A simulation framework using Python is…

Deep neural networks, costly to train and rich in intellectual property value, are increasingly threatened by model extraction attacks that compromise their confidentiality. Previous attacks have succeeded in reverse-engineering model…

Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to…

Over the last decade, Neural Networks (NNs) have been widely used in numerous applications including safety-critical ones such as autonomous systems. Despite their emerging adoption, it is well known that NNs are susceptible to Adversarial…