相关论文: Simulating Unknown Target Models for Query-Efficie…

The success of deep learning research has catapulted deep models into production systems that our society is becoming increasingly dependent on, especially in the image and video domains. However, recent work has shown that these largely…

Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their training dataset. While some model inversion attacks have been…

Deep Neural Networks (DNNs) are susceptible to model stealing attacks, which allows a data-limited adversary with no knowledge of the training dataset to clone the functionality of a target model, just by using black-box query access. Such…

Existing black-box attacks have demonstrated promising potential in creating adversarial examples (AE) to deceive deep learning models. Most of these attacks need to handle a vast optimization space and require a large number of queries,…

Access to online visual search engines implies sharing of private user content - the query images. We introduce the concept of targeted mismatch attack for deep learning based retrieval systems to generate an adversarial image to conceal…

The widespread use of deep learning technology across various industries has made deep neural network models highly valuable and, as a result, attractive targets for potential attackers. Model extraction attacks, particularly query-based…

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

Blackbox adversarial attacks can be categorized into transfer- and query-based attacks. Transfer methods do not require any feedback from the victim model, but provide lower success rates compared to query-based methods. Query attacks often…

Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…

There has been recently a growing interest in studying adversarial examples on natural language models in the black-box setting. These methods attack natural language classifiers by perturbing certain important words until the classifier…

Multitask learning (MTL) has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, to solve them simultaneously while minimizing data sharing…

Web-scraped datasets are vulnerable to data poisoning, which can be used for backdooring deep image classifiers during training. Since training on large datasets is expensive, a model is trained once and re-used many times. Unlike…

Black box attacks, where adversaries have limited knowledge of the target model, pose a significant threat to machine learning systems. Adversarial examples generated with a substitute model often suffer from limited transferability to the…

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of…

In-context learning (ICL) has become a powerful, data-efficient paradigm for text classification using large language models. However, its robustness against realistic adversarial threats remains largely unexplored. We introduce ICL-Evader,…

Neural networks play an increasingly important role in the field of machine learning and are included in many applications in society. Unfortunately, neural networks suffer from adversarial samples generated to attack them. However, most of…

Decision-based evasion attacks repeatedly query a black-box classifier to generate adversarial examples. Prior work measures the cost of such attacks by the total number of queries made to the classifier. We argue this metric is flawed.…

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…

Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning…

An adversary who aims to steal a black-box model repeatedly queries the model via a prediction API to learn a function that approximates its decision boundary. Adversarial approximation is non-trivial because of the enormous combinations of…