相关论文: BliMe Linter

Due to the rising concerns on privacy protection, how to build machine learning (ML) models over different data sources with security guarantees is gaining more popularity. Vertical federated learning (VFL) describes such a case where ML…

Open-source code is pervasive. In this setting, embedded vulnerabilities are spreading to downstream software at an alarming rate. While such vulnerabilities are generally identified and addressed rapidly, inconsistent maintenance policies…

Machine unlearning enables data holders to remove the contribution of their specified samples from trained models to protect their privacy. However, it is paradoxical that most unlearning methods require the unlearning requesters to firstly…

Fine-tuning Large Language Models (LLMs) on sensitive datasets carries a substantial risk of unintended memorization and leakage of Personally Identifiable Information (PII), which can violate privacy regulations and compromise individual…

Novel hardware-aided trusted execution environments, as provided by Intel's Software Guard Extensions (SGX), enable to execute applications in a secure context that enforces confidentiality and integrity of the application state even when…

The proliferation of Internet of Things (IoT) devices has introduced significant security challenges, primarily due to the opacity of firmware components and the complexity of supply chain dependencies. IoT firmware frequently relies on…

Reliability of complex Cyber-Physical Systems is necessary to guarantee availability and/or safety of the provided services. Diverse and complex fault tolerance policies are adopted to enhance reliability, that include a varied mix of…

Code secrets are sensitive assets for software developers, and their leakage poses significant cybersecurity risks. While the rapid development of AI code assistants powered by Code Large Language Models (CLLMs), CLLMs are shown to…

Memory corruption vulnerabilities remain one of the most severe threats to software security. They often allow attackers to achieve arbitrary code execution by redirecting a vulnerable program's control flow. While Control Flow Integrity…

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…

Code quality is of paramount importance in all types of software development settings. Our work seeks to enable Machine Learning (ML) engineers to write better code by helping them find and fix instances of Data Leakage in their models.…

Large language models (LLMs) have emerged as a powerful foundation for intelligent reasoning and decision-making, demonstrating substantial impact across a wide range of domains and applications. However, their massive parameter scales and…

Blind quantum computing enables a client, who does not have enough quantum technologies, to delegate her quantum computing to a remote quantum server in such a way that her privacy is protected against the server. Some blind quantum…

The application layer of Bluetooth Low Energy (BLE) is a growing source of security vulnerabilities, as developers often neglect to implement critical protections such as encryption, authentication, and freshness. While formal verification…

Deep learning models, particularly Long Short-Term Memory (LSTM) networks, are widely used in time series forecasting due to their ability to capture complex temporal dependencies. However, evaluation integrity is often compromised by data…

Since the advent of Spectre attacks, researchers and practitioners have developed a range of hardware and software measures to counter transient execution attacks. A prime example of such mitigation is speculative load hardening in LLVM,…

Understanding and engaging with privacy policies is crucial for online privacy, yet these documents remain notoriously complex and difficult to navigate. We present PRISMe, an interactive browser extension that combines LLM-based policy…

Over the past few years, a tremendous growth of machine learning was brought about by a significant increase in adoption of cloud-based services. As a result, various solutions have been proposed in which the machine learning models run on…

Motivated by privacy preservation for outsourced data, data-oblivious external memory is a computational framework where a client performs computations on data stored at a semi-trusted server in a way that does not reveal her data to the…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…