Related papers: CONFLLVM: A Compiler for Enforcing Data Confidenti…

If we can automatically derive compiler optimizations, we might be able to sidestep some of the substantial engineering challenges involved in creating and maintaining a high-quality compiler. We developed Souper, a synthesizing…

We present OnPrem$.$LLM, a Python-based toolkit for applying large language models (LLMs) to sensitive, non-public data in offline or restricted environments. The system is designed for privacy-preserving use cases and provides prebuilt…

Data contamination presents a critical barrier preventing widespread industrial adoption of advanced software engineering techniques that leverage code language models (CLMs). This phenomenon occurs when evaluation data inadvertently…

Current compiler optimization reports often present complex, technical information that is difficult for programmers to interpret and act upon effectively. This paper assesses the capability of large language models (LLM) to understand…

Confidential computing safeguards sensitive computations from untrusted clouds, with Confidential Virtual Machines (CVMs) providing a secure environment for guest OS. However, CVMs often come with large and vulnerable operating system…

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…

Accurate identification of software vulnerabilities is crucial for system integrity. Vulnerability datasets, often derived from the National Vulnerability Database (NVD) or directly from GitHub, are essential for training machine learning…

We present Low*, a language for low-level programming and verification, and its application to high-assurance optimized cryptographic libraries. Low* is a shallow embedding of a small, sequential, well-behaved subset of C in F*, a…

Over the years, the complexity of the Linux Security Module (LSM) is keeping increasing, and the count of the authorization hooks is nearly doubled. It is important to provide up-to-date measurement results of LSM for system practitioners…

Crary and Sullivan's Relaxed Memory Calculus (RMC) proposed a new declarative approach for writing low-level shared memory concurrent programs in the presence of modern relaxed-memory multi-processor architectures and optimizing compilers.…

Control-flow leakage (CFL) attacks enable an attacker to expose control-flow decisions of a victim program via side-channel observations. Linearization (i.e., elimination) of secret-dependent control flow is the main countermeasure against…

Fraud detection and anti-money-laundering (AML) compliance are high-value domains for large language models (LLMs), but their serving requirements differ sharply from generic chat workloads. Compliance prompts are often prefix-heavy,…

Privacy-preserving technologies have introduced a paradigm shift that allows for realizable secure computing in real-world systems. The significant barrier to the practical adoption of these primitives is the computational and communication…

The integration of large language models (LLMs) into cyber security applications presents both opportunities and critical safety risks. We introduce CyberLLMInstruct, a dataset of 54,928 pseudo-malicious instruction-response pairs spanning…

Selective data protection is a promising technique to defend against the data leakage attack. In this paper, we revisit technical challenges that were neglected when applying this protection to real applications. These challenges include…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

In the digital era, accidental exposure of sensitive information such as API keys, tokens, and credentials is a growing security threat. While most prior work focuses on detecting secrets in source code, leakage in software issue reports…

Background: Leaking sensitive information - such as API keys, tokens, and credentials - in source code remains a persistent security threat. Traditional regex and entropy-based tools often generate high false positives due to limited…

This paper reports on initial experiments using J Moore's Codewalker to reason about programs compiled to the Low-Level Virtual Machine (LLVM) intermediate form. Previously, we reported on a translator from LLVM to the applicative subset of…

Traditional security mechanisms isolate resources from users who should not access them. We reflect the compositional nature of such security mechanisms back into the structure of LLMs to build a provably secure LLM; that we term SecureLLM.…