相关论文: Marich: A Query-efficient Distributionally Equival…

We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…

Machine Learning (ML) has made unprecedented progress in the past several decades. However, due to the memorability of the training data, ML is susceptible to various attacks, especially Membership Inference Attacks (MIAs), the objective of…

Machine Learning as a Service (MLaaS) enables users to leverage powerful machine learning models through cloud-based APIs, offering scalability and ease of deployment. However, these services are vulnerable to model extraction attacks,…

Despite significant improvements in natural language understanding models with the advent of models like BERT and XLNet, these neural-network based classifiers are vulnerable to blackbox adversarial attacks, where the attacker is only…

Large language models (LLMs) are inherently vulnerable to unintended privacy breaches. Consequently, systematic red-teaming research is essential for developing robust defense mechanisms. However, current data extraction methods suffer from…

Many machine learning algorithms and classifiers are available only via API queries as a ``black-box'' -- that is, the downstream user has no ability to change, re-train, or fine-tune the model on a particular target distribution. Indeed,…

Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security…

Any search or sampling algorithm for solution of inverse problems needs guidance to be efficient. Many algorithms collect and apply information about the problem on the fly, and much improvement has been made in this way. However, as a…

It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can perform a training data extraction attack to recover…

Large language models (LLMs) increasingly rely on retrieving information from external corpora. This creates a new attack surface: indirect prompt injection (IPI), where hidden instructions are planted in the corpora and hijack model…

Statistical model checking is a class of sequential algorithms that can verify specifications of interest on an ensemble of cyber-physical systems (e.g., whether 99% of cars from a batch meet a requirement on their energy efficiency). These…

To develop a trustworthy AI system, which aim to identify the input regions that most influence the models decisions. The primary task of existing attribution methods lies in efficiently and accurately identifying the relationships among…

Model extraction (ME) attacks represent one major threat to Machine-Learning-as-a-Service (MLaaS) platforms by ``stealing'' the functionality of confidential machine-learning models through querying black-box APIs. Over seven years have…

Consider learning a policy purely on the basis of demonstrated behavior -- that is, with no access to reinforcement signals, no knowledge of transition dynamics, and no further interaction with the environment. This *strictly batch…

We study the problem of exploration in Reinforcement Learning and present a novel model-free solution. We adopt an information-theoretical viewpoint and start from the instance-specific lower bound of the number of samples that have to be…

Active learning is commonly used to train label-efficient models by adaptively selecting the most informative queries. However, most active learning strategies are designed to either learn a representation of the data (e.g., embedding or…

Artificial intelligence systems are prevalent in everyday life, with use cases in retail, manufacturing, health, and many other fields. With the rise in AI adoption, associated risks have been identified, including privacy risks to the…

With growing popularity, deep learning (DL) models are becoming larger-scale, and only the companies with vast training datasets and immense computing power can manage their business serving such large models. Most of those DL models are…

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science,…

Recent studies have demonstrated the vulnerability of sequential recommender systems to Model Extraction Attacks (MEAs). MEAs collect responses from recommender systems to replicate their functionality, enabling unauthorized deployments and…