Related papers: Extending Defensive Distillation
The security of deep learning (DL) systems is an extremely important field of study as they are being deployed in several applications due to their ever-improving performance to solve challenging tasks. Despite overwhelming promises, the…
Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms…
Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary…
Deep learning models are vulnerable to adversarial examples and make incomprehensible mistakes, which puts a threat on their real-world deployment. Combined with the idea of adversarial training, preprocessing-based defenses are popular and…
Due to their massive success in various domains, deep learning techniques are increasingly used to design network intrusion detection solutions that detect and mitigate unknown and known attacks with high accuracy detection rates and…
Modern image classification systems are often built on deep neural networks, which suffer from adversarial examples--images with deliberately crafted, imperceptible noise to mislead the network's classification. To defend against…
Knowledge distillation from proprietary LLM APIs poses a growing threat to model providers, yet defenses against this attack remain fragmented and unevaluated. We present DistillGuard, a framework for systematically evaluating output-level…
In this article I describe a research agenda for securing machine learning models against adversarial inputs at test time. This article does not present results but instead shares some of my thoughts about where I think that the field needs…
With the development of high computational devices, deep neural networks (DNNs), in recent years, have gained significant popularity in many Artificial Intelligence (AI) applications. However, previous efforts have shown that DNNs were…
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding…
In this paper, we propose a new approach called MemLoss to improve the adversarial training of machine learning models. MemLoss leverages previously generated adversarial examples, referred to as 'Memory Adversarial Examples,' to enhance…
Data poisoning attacks aim to manipulate the model produced by a learning algorithm by adversarially modifying the training set. We consider differential privacy as a defensive measure against this type of attack. We show that such learners…
From past couple of years there is a cycle of researchers proposing a defence model for adversaries in machine learning which is arguably defensible to most of the existing attacks in restricted condition (they evaluate on some bounded…
Convolutional neural networks (CNNs) excel in computer vision but are susceptible to adversarial attacks, crafted perturbations designed to mislead predictions. Despite advances in adversarial training, a gap persists between model accuracy…
Defensive deception is a promising approach for cyber defense. Via defensive deception, the defender can anticipate attacker actions; it can mislead or lure attacker, or hide real resources. Although defensive deception is increasingly…
The superiority of deep learning performance is threatened by safety issues for itself. Recent findings have shown that deep learning systems are very weak to adversarial examples, an attack form that was altered by the attacker's intent to…
Intentionally crafted adversarial samples have effectively exploited weaknesses in deep neural networks. A standard method in adversarial robustness assumes a framework to defend against samples crafted by minimally perturbing a sample such…
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the training phase of deep neural networks make…
Ongoing research has proposed several methods to defend neural networks against adversarial examples, many of which researchers have shown to be ineffective. We ask whether a strong defense can be created by combining multiple (possibly…
Nowadays, we are more and more reliant on Deep Learning (DL) models and thus it is essential to safeguard the security of these systems. This paper explores the security issues in Deep Learning and analyses, through the use of experiments,…