Related papers: QueryCheetah: Fast Automated Discovery of Attribut…
Differential privacy (DP) allows data analysts to query databases that contain users' sensitive information while providing a quantifiable privacy guarantee to users. Recent interactive DP systems such as APEx provide accuracy guarantees…
Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…
Query-based black-box attacks have emerged as a significant threat to machine learning systems, where adversaries can manipulate the input queries to generate adversarial examples that can cause misclassification of the model. To counter…
Data poisoning attacks pose significant threats to machine learning models by introducing malicious data into the training process, thereby degrading model performance or manipulating predictions. Detecting and sifting out poisoned data is…
In distributed learning settings, models are iteratively updated with shared gradients computed from potentially sensitive user data. While previous work has studied various privacy risks of sharing gradients, our paper aims to provide a…
The collection and availability of big data, combined with advances in pre-trained models (e.g., BERT, XLNET, etc), have revolutionized the predictive performance of modern natural language processing tasks, ranging from text classification…
We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice. While previous works have taken steps toward evaluating privacy loss through poisoning attacks or…
With an increase in low-cost machine learning APIs, advanced machine learning models may be trained on private datasets and monetized by providing them as a service. However, privacy researchers have demonstrated that these models may leak…
Membership Inference Attacks exploit the vulnerabilities of exposing models trained on customer data to queries by an adversary. In a recently proposed implementation of an auditing tool for measuring privacy leakage from sensitive…
Machine learning (ML), especially deep neural networks (DNNs) have been widely used in various applications, including several safety-critical ones (e.g. autonomous driving). As a result, recent research about adversarial examples has…
Empirical inference attacks are a popular approach for evaluating the privacy risk of data release mechanisms in practice. While an active attack literature exists to evaluate machine learning models or synthetic data release, we currently…
This work introduces the Query/Hit (Q/H) learning model. The setup consists of two agents. One agent, Alice, has access to a streaming source, while the other, Bob, does not have direct access to the source. Communication occurs through…
Recent Searchable Symmetric Encryption (SSE) schemes enable secure searching over an encrypted database stored in a server while limiting the information leaked to the server. These schemes focus on hiding the access pattern, which refers…
This research paper explores the privacy and security threats posed to an Agentic AI system with direct access to database systems. Such access introduces significant risks, including unauthorized retrieval of sensitive information,…
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…
One of the data security and privacy concerns is of insider threats, where legitimate users of the system abuse the access privileges they hold. The insider threat to data security means that an insider steals or leaks sensitive personal…
Recent advances in synthetic data generation (SDG) have been hailed as a solution to the difficult problem of sharing sensitive data while protecting privacy. SDG aims to learn statistical properties of real data in order to generate…
Attribute inference - the process of analyzing publicly available data in order to uncover hidden information - has become a major threat to privacy, given the recent technological leap in machine learning. One way to tackle this threat is…
Differential privacy is the state-of-the-art definition for privacy, guaranteeing that any analysis performed on a sensitive dataset leaks no information about the individuals whose data are contained therein. In this thesis, we develop…
In this work, we provide an industry research view for approaching the design, deployment, and operation of trustworthy Artificial Intelligence (AI) inference systems. Such systems provide customers with timely, informed, and customized…