Related papers: Adversaries Can Misuse Combinations of Safe Models

The existence of adversarial attacks (or adversarial examples) brings huge concern about the machine learning (ML) model's safety issues. For many safety-critical ML tasks, such as financial forecasting, fraudulent detection, and anomaly…

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

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…

This paper investigates the problem of synthesizing proactive defense systems in which the defender can allocate deceptive targets and modify the cost of actions for the attacker who aims to compromise security assets in this system. We…

Machine learning (ML) defenses protect against various risks to security, privacy, and fairness. Real-life models need simultaneous protection against multiple different risks which necessitates combining multiple defenses. But combining…

Recent research has shown Deep Neural Networks (DNNs) to be vulnerable to adversarial examples that induce desired misclassifications in the models. Such risks impede the application of machine learning in security-sensitive domains.…

In autonomous driving, behavior prediction is fundamental for safe motion planning, hence the security and robustness of prediction models against adversarial attacks are of paramount importance. We propose a novel adversarial backdoor…

Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to capabilities that pose extreme risks, such as offensive cyber…

AI leaders and safety reports increasingly warn that advances in model reasoning may enable biological misuse, including by low-expertise users, while major labs describe safeguards as expanding but still evolving rather than settled. This…

With the current ongoing debate about fairness, explainability and transparency of machine learning models, their application in high-impact clinical decision-making systems must be scrutinized. We consider a real-life example of risk…

While convolutional neural networks (CNNs) have achieved excellent performances in various computer vision tasks, they often misclassify with malicious samples, a.k.a. adversarial examples. Adversarial training is a popular and…

Automated content filtering and moderation is an important tool that allows online platforms to build striving user communities that facilitate cooperation and prevent abuse. Unfortunately, resourceful actors try to bypass automated filters…

Guaranteeing the security of transactional systems is a crucial priority of all institutions that process transactions, in order to protect their businesses against cyberattacks and fraudulent attempts. Adversarial attacks are novel…

A comprehensive approach to addressing catastrophic risks from AI models should cover the full model lifecycle. This paper explores contingency plans for cases where pre-deployment risk management falls short: where either very dangerous…

Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white…

Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of transparency for agents through the lens of transferable adversarial example attacks. In…

Federated learning distributes model training among a multitude of agents, who, guided by privacy concerns, perform training using their local data but share only model parameter updates, for iterative aggregation at the server. In this…

With machine learning models being used for more sensitive applications, we rely on interpretability methods to prove that no discriminating attributes were used for classification. A potential concern is the so-called "fair-washing" -…

Deep learning has emerged as a strong and efficient framework that can be applied to a broad spectrum of complex learning problems which were difficult to solve using the traditional machine learning techniques in the past. In the last few…

Backdoor attacks represent a subtle yet effective class of cyberattacks targeting AI models, primarily due to their stealthy nature. The model behaves normally on clean data but exhibits malicious behavior only when the attacker embeds a…