相关论文: OSNIP: Breaking the Privacy-Utility-Efficiency Tri…

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…

Pretrained knowledge memorized in LLMs raises critical concerns over safety and privacy, which has motivated LLM Unlearning as a technique for selectively removing the influences of undesirable knowledge. Existing approaches, rooted in…

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural…

The study of privacy-preserving Natural Language Processing (NLP) has gained rising attention in recent years. One promising avenue studies the integration of Differential Privacy in NLP, which has brought about innovative methods in a…

Open Semantic Mapping (OSM) is a key technology in robotic perception, combining semantic segmentation and SLAM techniques. This paper introduces a dynamically configurable and highly automated LLM/LVLM-powered pipeline for evaluating OSM…

In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versatility, DP-SGD…

The use of Machine Learning (ML) for data-driven decision-making often relies on access to sensitive datasets, which introduces privacy challenges. Traditional encryption methods protect data at rest or in transit but fail to secure it…

Reliable pseudo-labels from unlabeled data play a key role in semi-supervised object detection (SSOD). However, the state-of-the-art SSOD methods all rely on pseudo-labels with high confidence, which ignore valuable pseudo-labels with lower…

The ability to control for the kinds of information encoded in neural representation has a variety of use cases, especially in light of the challenge of interpreting these models. We present Iterative Null-space Projection (INLP), a novel…

Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider. Previous research on secure reasoning…

Density-adaptive domain discretization is essential for high-utility privacy-preserving analytics but remains challenging under Local Differential Privacy (LDP) due to the privacy-budget costs associated with iterative refinement. We…

Large Language Models (LLMs) represent valuable intellectual property (IP), reflecting significant investments in training data, compute, and expertise. Deploying these models on partially trusted or insecure devices introduces substantial…

This work addresses the computational challenge of enforcing privacy for agentic Large Language Models (LLMs), where privacy is governed by the contextual integrity framework. Indeed, existing defenses rely on LLM-mediated checking stages…

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…

Privacy in form of anonymous communication could be comparably both faster and harder to break in optical routers than in today's anonymous IP networks based on The Onion Routing (Tor). Implementing the practical privacy…

Open-set semi-supervised learning (OSSL) leverages unlabeled data containing both in-distribution (ID) and unknown out-of-distribution (OOD) samples, aiming simultaneously to improve closed-set accuracy and detect novel OOD instances.…

Large language models (LLMs) are increasingly integrated into real-time machine learning applications, where safeguarding user privacy is paramount. Traditional differential privacy mechanisms often struggle to balance privacy and accuracy,…

Privacy-sensitive users require deploying large language models (LLMs) within their own infrastructure (on-premises) to safeguard private data and enable customization. However, vulnerabilities in local environments can lead to unauthorized…

User language data can contain highly sensitive personal content. As such, it is imperative to offer users a strong and interpretable privacy guarantee when learning from their data. In this work, we propose SentDP: pure local differential…

Privacy-preserving location-base services (LBS) have been proposed to protect users' location privacy. However, there are still some problems in existing schemes: (1) a semi-trusted third party (TTP) is required; or (2) both the computation…