Related papers: Too Private to Tell: Practical Token Theft Attacks…

Privacy and security have rapidly emerged as first order design constraints. Users now demand more protection over who can see their data (confidentiality) as well as how it is used (control). Here, existing cryptographic techniques for…

Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain. Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage…

Machine Learning (ML) algorithms are susceptible to adversarial attacks and deception both during training and deployment. Automatic reverse engineering of the toolchains behind these adversarial machine learning attacks will aid in…

This investigation reveals a novel exploit derived from PNG image file formats, specifically their alpha transparency layer, and its potential to fool multiple AI vision systems. Our method uses this alpha layer as a clandestine channel…

Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query…

Federated learning (FL) has been widely studied recently due to its property to collaboratively train data from different devices without sharing the raw data. Nevertheless, recent studies show that an adversary can still be possible to…

Our voice encodes a uniquely identifiable pattern which can be used to infer private attributes, such as gender or identity, that an individual might wish not to reveal when using a speech recognition service. To prevent attribute inference…

Generative AI systems increasingly expose powerful reasoning and image refinement capabilities through user-facing chatbot interfaces. In this work, we show that the na\"ive exposure of such capabilities fundamentally undermines modern…

A large amount of transaction data containing associations between individuals and sensitive information flows everyday into data stores. Examples include web queries, credit card transactions, medical exam records, transit database…

Machine Learning (ML) models are known to be vulnerable to adversarial inputs and researchers have demonstrated that even production systems, such as self-driving cars and ML-as-a-service offerings, are susceptible. These systems represent…

Neural network-based image classifiers are powerful tools for computer vision tasks, but they inadvertently reveal sensitive attribute information about their classes, raising concerns about their privacy. To investigate this privacy…

We present foundation language models developed to power Apple Intelligence features, including a ~3 billion parameter model designed to run efficiently on devices and a large server-based language model designed for Private Cloud Compute.…

Artificial intelligence and machine learning have been integrated into all aspects of our lives and the privacy of personal data has attracted more and more attention. Since the generation of the model needs to extract the effective…

In the standard privacy-preserving Machine learning as-a-service (MLaaS) model, the client encrypts data using homomorphic encryption and uploads it to a server for computation. The result is then sent back to the client for decryption. It…

Data privacy has become an increasingly important issue in Machine Learning (ML), where many approaches have been developed to tackle this challenge, e.g. cryptography (Homomorphic Encryption (HE), Differential Privacy (DP), etc.) and…

The current amount of IoT devices and their limitations has come to serve as a motivation for malicious entities to take advantage of such devices and use them for their own gain. To protect against cyberattacks in IoT devices, Machine…

Over the last decade, Artificial Intelligence (AI) has become increasingly popular, especially with the use of chatbots such as ChatGPT, Gemini, and DALL-E. With this rise, large language models (LLMs) and Generative AI (GenAI) have also…

Current methods for authentication and key agreement based on public-key cryptography are vulnerable to quantum computing. We propose a novel approach based on artificial intelligence research in which communicating parties are viewed as…

Gemini is increasingly used to perform tasks on behalf of users, where function-calling and tool-use capabilities enable the model to access user data. Some tools, however, require access to untrusted data introducing risk. Adversaries can…

Generative A.I. models have emerged as versatile tools across diverse industries, with applications in privacy-preserving data sharing, computational art, personalization of products and services, and immersive entertainment. Here, we…