Related papers: Analyzing Accuracy Loss in Randomized Smoothing De…
Federated learning enables training machine learning models while preserving the privacy of participants. Surprisingly, there is no differentially private distributed method for smooth, non-convex optimization problems. The reason is that…
Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…
Machine Learning (ML) models have been utilized for malware detection for over two decades. Consequently, this ignited an ongoing arms race between malware authors and antivirus systems, compelling researchers to propose defenses for…
Machine learning based system are increasingly being used for sensitive tasks such as security surveillance, guiding autonomous vehicle, taking investment decisions, detecting and blocking network intrusion and malware etc. However, recent…
Recent studies have shown that deep neural networks are vulnerable to adversarial examples, but most of the methods proposed to defense adversarial examples cannot solve this problem fundamentally. In this paper, we theoretically prove that…
Sensitivity to adversarial noise hinders deployment of machine learning algorithms in security-critical applications. Although many adversarial defenses have been proposed, robustness to adversarial noise remains an open problem. The most…
Deep neural networks (DNNs) are known to be vulnerable to adversarial examples. Existing works have mostly focused on either digital adversarial examples created via small and imperceptible perturbations, or physical-world adversarial…
ML is shifting from the cloud to the edge. Edge computing reduces the surface exposing private data and enables reliable throughput guarantees in real-time applications. Of the panoply of devices deployed at the edge, resource-constrained…
From face recognition systems installed in phones to self-driving cars, the field of AI is witnessing rapid transformations and is being integrated into our everyday lives at an incredible pace. Any major failure in these system's…
The use of machine learning (ML) has become increasingly prevalent in various domains, highlighting the importance of understanding and ensuring its safety. One pressing concern is the vulnerability of ML applications to model stealing…
Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce drastically different outputs. Many defense methods require…
Deep Neural Networks (DNNs) are known to be susceptible to adversarial examples. Adversarial examples are maliciously crafted inputs that are designed to fool a model, but appear normal to human beings. Recent work has shown that pixel…
Deep Neural Networks (DNNs) have been shown to be vulnerable against adversarial examples, which are data points cleverly constructed to fool the classifier. Such attacks can be devastating in practice, especially as DNNs are being applied…
The robustness of deep neural networks (DNNs) against adversarial example attacks has raised wide attention. For smoothed classifiers, we propose the worst-case adversarial loss over input distributions as a robustness certificate. Compared…
Deep neural networks (DNNs) are vulnerable to adversarial noise. Preprocessing based defenses could largely remove adversarial noise by processing inputs. However, they are typically affected by the error amplification effect, especially in…
Machine learning (ML) techniques are increasingly common in security applications, such as malware and intrusion detection. However, ML models are often susceptible to evasion attacks, in which an adversary makes changes to the input (such…
Although large language models (LLMs) have achieved great success in vast real-world applications, their vulnerabilities towards noisy inputs have significantly limited their uses, especially in high-stake environments. In these contexts,…
Randomized smoothing is sound when using infinite precision. However, we show that randomized smoothing is no longer sound for limited floating-point precision. We present a simple example where randomized smoothing certifies a radius of…
Machine Learning in general and Deep Learning in particular has gained much interest in the recent decade and has shown significant performance improvements for many Computer Vision or Natural Language Processing tasks. In order to deal…
Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some…