相关论文: Finding Missing Input Validation in TEEs via LLM-A…

Public agencies are beginning to consider large language models (LLMs) as decision-support tools for grant evaluation. This creates a practical governance problem: the model and scoring rubric should not be exposed in a way that allows…

As an essential technology underpinning trusted computing, the trusted execution environment (TEE) allows one to launch computation tasks on both on- and off-premises data while assuring confidentiality and integrity. This article provides…

Trusted Execution Environments (TEEs) protect sensitive code and data from the operating system, hypervisor, or other untrusted software. Different solutions exist, each proposing different features. Abstraction layers aim to unify the…

Large Language Models (LLMs) deployed on mobile devices offer benefits like user privacy and reduced network latency, but introduce a significant security risk: the leakage of proprietary models to end users. To mitigate this risk, we…

Hardware-secured remote attestation is essential to establishing trust in the integrity of confidential virtual machines (cVMs), but is difficult to use in practice because verifying attestation evidence requires the use of…

Commercial Large Language Model (LLM) APIs create a fundamental trust problem: users pay for specific models but have no guarantee that providers deliver them faithfully. Providers may covertly substitute cheaper alternatives (e.g.,…

A trusted execution environment (TEE) such as Intel Software Guard Extension (SGX) runs a remote attestation to prove to a data owner the integrity of the initial state of an enclave, including the program to operate on her data. For this…

Symbolic execution is a key technology in software testing, which generates test cases by collecting symbolic path constraints and then solving constraints with SMT solvers. Symbolic execution has been proven helpful in generating…

Process attestation systems verify that a continuous physical process, such as human authorship, actually occurred, rather than merely checking system state. These systems face a fundamental dependability challenge: the evidence collection…

As an emerging technique for confidential computing, trusted execution environment (TEE) receives a lot of attention. To better develop, deploy, and run secure applications on a TEE platform such as Intel's SGX, both academic and industrial…

Symbolic execution detects vulnerabilities with precision, but applying it to large codebases requires harnesses that set up symbolic state, model dependencies, and specify assertions. Writing these harnesses has traditionally been a manual…

Trusted Execution Environments (TEEs) provide hardware-based isolation to protect sensitive data and computations from potentially compromised operating systems (OS). However, TEE applications inevitably interact with the untrusted OS…

Data hosted in a cloud environment can be subject to attacks from a higher privileged adversary, such as a malicious or compromised cloud provider. To provide confidentiality and integrity even in the presence of such an adversary, a number…

High-privilege LLM agents that autonomously process external documentation are increasingly trusted to automate tasks by reading and executing project instructions, yet they are granted terminal access, filesystem control, and outbound…

Symbolic execution is an important software analysis technique which benefits downstream tasks such as software testing and debugging. However, several limitations hinder symbolic execution from application on real-world software. One of…

Modern Large Language Model (LLM)-based programming agents often rely on test execution feedback to refine their generated code. These tests are synthetically generated by LLMs. However, LLMs may produce invalid or hallucinated test cases,…

Trusted Execution Environments (TEEs) are rapidly emerging as a root-of-trust for protecting sensitive applications and data using hardware-backed isolated worlds of execution. TEEs provide robust assurances regarding critical algorithm…

Large Language Models (LLMs) are widely used for downstream tasks such as tabular classification, where ensuring fairness in their outputs is critical for inclusivity, equal representation, and responsible AI deployment. This study…

Using cloud-based applications comes with privacy implications, as the end-user looses control over their data. While encrypting all data on the client is possible, it largely reduces the usefulness of database management systems (DBMS)…

Assessing the quality of Large Language Model (LLM) outputs presents a critical challenge. Previous methods either rely on text-level information (e.g., reward models, majority voting), which can overfit to superficial cues, or on…