On Membership Inference Attacks in Knowledge Distillation

Nowadays, Large Language Models LLMs are trained on huge datasets, some including sensitive information. This poses a serious privacy concern because privacy attacks such as Membership Inference Attacks MIAs may detect this sensitive information. While knowledge distillation compresses LLMs into...

Improved Algorithms for Differentially Private Language Model Alignment

Language model alignment is crucial for ensuring that large language models LLMs align with human preferences, yet it often involves sensitive user data, raising significant privacy concerns. While prior work has integrated differential privacy DP with alignment techniques, their performance...

Source Anonymity for Private Random Walk Decentralized Learning

This paper considers random walk-based decentralized learning, where at each iteration of the learning process, one user updates the model and sends it to a randomly chosen neighbor until a convergence criterion is met. Preserving data privacy is a central concern and open problem in decentralize...

NCorr-FP: a Neighbourhood-Based Correlation-Preserving Fingerprinting Scheme for Intellectual Property Protection of Structured Data

Ensuring data ownership and traceability of unauthorised redistribution are central to safeguarding intellectual property in shared data environments. Data fingerprinting addresses these challenges by embedding recipient-specific marks into the data, typically via content modifications. We propos...

Enhancing Noisy Functional Encryption for Privacy-Preserving Machine Learning

Functional encryption FE has recently attracted interest in privacy-preserving machine learning PPML for its unique ability to compute specific functions on encrypted data. A related line of work focuses on noisy FE, which ensures differential privacy in the output while keeping the data encrypte...

Optimal Regret of Bernoulli Bandits under Global Differential Privacy

As sequential learning algorithms are increasingly applied to real life, ensuring data privacy while maintaining their utilities emerges as a timely question. In this context, regret minimisation in stochastic bandits under $ε$-global Differential Privacy DP has been widely studied. Unlike bandit...

Privacy Risks and Preservation Methods in Explainable Artificial Intelligence: a Scoping Review

Explainable Artificial Intelligence XAI has emerged as a pillar of Trustworthy AI and aims to bring transparency in complex models that are opaque by nature. Despite the benefits of incorporating explanations in models, an urgent need is found in addressing the privacy concerns of providing this...

Encrypted Federated Search Using Homomorphic Encryption

The sharing of information between agencies is effective in dealing with cross-jurisdictional criminal activities; however, such sharing is often restricted due to concerns about data privacy, ownership, and compliance. Towards this end, this work has introduced a privacy-preserving federated...

Enhanced Outsourced and Secure Inference for Tall Sparse Decision Trees

A decision tree is an easy-to-understand tool that has been widely used for classification tasks. On the one hand, due to privacy concerns, there has been an urgent need to create privacy-preserving classifiers that conceal the user's input from the classifier. On the other hand, with the rise of...

Privacy Preserving Machine Learning Model Personalization through Federated Personalized Learning

The widespread adoption of Artificial Intelligence AI has been driven by significant advances in intelligent system research. However, this progress has raised concerns about data privacy, leading to a growing awareness of the need for privacy-preserving AI. In response, there has been a seismic...

Preserving Privacy and Utility in LLM-Based Product Recommendations

Large Language Model LLM-based recommendation systems leverage powerful language models to generate personalized suggestions by processing user interactions and preferences. Unlike traditional recommendation systems that rely on structured data and collaborative filtering, LLM-based models proces...

CryptoUNets: Applying Convolutional Networks to Encrypted Data for Biomedical Image Segmentation

In this manuscript, we demonstrate the feasibility of a privacy-preserving U-Net deep learning inference framework, namely, homomorphic encryption-based U-Net inference. That is, U-Net inference can be performed solely using homomorphic encryption techniques. To our knowledge, this is the first...

SoK: Enhancing Privacy-Preserving Software Development from a Developers' Perspective

In software development, privacy preservation has become essential with the rise of privacy concerns and regulations such as GDPR and CCPA. While several tools, guidelines, methods, methodologies, and frameworks have been proposed to support developers embedding privacy into software applications...

Silenzio: Secure Non-Interactive Outsourced MLP Training

Outsourcing the ML training to cloud providers presents a compelling opportunity for resource constrained clients, while it simultaneously bears inherent privacy risks, especially for highly sensitive training data. We introduce Silenzio, the first fully non-interactive outsourcing scheme for the...

Property-Preserving Hashing for $\Ell_1$-Distance Predicates: Applications to Countering Adversarial Input Attacks

Perceptual hashing is used to detect whether an input image is similar to a reference image with a variety of security applications. Recently, they have been shown to succumb to adversarial input attacks which make small imperceptible changes to the input image yet the hashing algorithm does not...

Fast Plaintext-Ciphertext Matrix Multiplication from Additively Homomorphic Encryption

Plaintext-ciphertext matrix multiplication PC-MM is an indispensable tool in privacy-preserving computations such as secure machine learning and encrypted signal processing. While there are many established algorithms for plaintext-plaintext matrix multiplication, efficiently computing...

Privacy-Preserving CNN Training with Transfer Learning: Two Hidden Layers

Whitepaper called Privacy-Preserving CNN Training With Transfer Learning: Two Hidden Layers...

Measuring Computational Universality of Fully Homomorphic Encryption

Many real-world applications, such as machine learning and graph analytics, involve combinations of linear and non-linear operations. As these applications increasingly handle sensitive data, there is a significant demand for privacy-preserving computation techniques capable of efficiently...

Detecting Pegasus Infections

This tool seems to do a pretty good job. The company's Mobile Threat Hunting feature uses a combination of malware signature-based detection, heuristics, and machine learning to look for anomalies in iOS and Android device activity or telltale signs of spyware infection. For paying iVerify...

Moodle authorization headers preserved between "emulated redirects"

A flaw was found in moodle. The cURL wrapper in Moodle strips HTTPAUTH and USERPWD headers during emulated redirects, but retains other original request headers, so HTTP authorization header information could be unintentionally sent in requests to redirect URLs...