Related papers: Availability Attacks Create Shortcuts
Neural networks trained on visual data are well-known to be vulnerable to often imperceptible adversarial perturbations. The reasons for this vulnerability are still being debated in the literature. Recently Ilyas et al. (2019) showed that…
Machine learning models are known to be vulnerable to adversarial attacks, namely perturbations of the data that lead to wrong predictions despite being imperceptible. However, the existence of "universal" attacks (i.e., unique…
Advanced Persistent Threats (APTs) are a main impendence in cyber security of computer networks. In 2015, a successful breach remains undetected 146 days on average, reported by [Fi16].With our work we demonstrate a feasible and fast way to…
Deep learning models are susceptible to adversarial attacks, where slight perturbations to input data lead to misclassification. Adversarial attacks become increasingly effective with access to information about the targeted classifier. In…
In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance. Recent studies have…
Embedded software is developed under the assumption that hardware execution is always correct. Fault attacks break and exploit that assumption. Through the careful introduction of targeted faults, an adversary modifies the control-flow or…
Adversarial attacks are a type of attack on machine learning models where an attacker deliberately modifies the inputs to cause the model to make incorrect predictions. Adversarial attacks can have serious consequences, particularly in…
We present \texttt{secml}, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including test-time evasion attacks to generate adversarial examples…
Deep neural networks (DNNs) are vulnerable to shortcut learning: rather than learning the intended task, they tend to draw inconclusive relationships between their inputs and outputs. Shortcut learning is ubiquitous among many failure cases…
Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…
Despite the great success achieved in machine learning (ML), adversarial examples have caused concerns with regards to its trustworthiness: A small perturbation of an input results in an arbitrary failure of an otherwise seemingly…
Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show…
Machine learning algorithms are vulnerable to poisoning attacks: An adversary can inject malicious points in the training dataset to influence the learning process and degrade the algorithm's performance. Optimal poisoning attacks have…
This paper addresses the ethical concerns arising from the use of unauthorized public data in deep learning models and proposes a novel solution. Specifically, building on the work of Huang et al. (2021), we extend their bi-level…
The rapid proliferation of Large Language Models (LLMs) has raised significant concerns about their security against adversarial attacks. In this work, we propose a novel approach to crafting universal jailbreaks and data extraction attacks…
Though Deep Neural Networks (DNN) show excellent performance across various computer vision tasks, several works show their vulnerability to adversarial samples, i.e., image samples with imperceptible noise engineered to manipulate the…
The adversarial attack literature contains a myriad of algorithms for crafting perturbations which yield pathological behavior in neural networks. In many cases, multiple algorithms target the same tasks and even enforce the same…
Deep neural networks have been shown to be vulnerable to adversarial examples deliberately constructed to misclassify victim models. As most adversarial examples have restricted their perturbations to $L_{p}$-norm, existing defense methods…
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models. However, this approach neglects the steady progression of…
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…