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

Confidential computing on GPUs, like NVIDIA H100, mitigates the security risks of outsourced Large Language Models (LLMs) by implementing strong isolation and data encryption. Nonetheless, this encryption incurs a significant performance…

Existing iterative compilation and machine-learning-based optimization techniques have been proven very successful in achieving better optimizations than the standard optimization levels of a compiler. However, they were not engineered to…

The code generation modules inside modern compilers such as GCC and LLVM, which use a limited number of CPU registers to store a large number of program variables, may introduce side-channel leaks even in software equipped with…

Proving only over source code that programs do not leak sensitive data leaves a gap between reasoning and reality that can only be filled by accounting for the behaviour of the compiler. Furthermore, software does not always have the luxury…

Constant-time programming is a countermeasure to prevent cache based attacks where programs should not perform memory accesses that depend on secrets. In some cases this policy can be safely relaxed if one can prove that the program does…

Large Language Models (LLMs) have emerged as promising tools for malware detection by analyzing code semantics, identifying vulnerabilities, and adapting to evolving threats. However, their reliability under adversarial compiler-level…

It is common to prove by reasoning over source code that programs do not leak sensitive data. But doing so leaves a gap between reasoning and reality that can only be filled by accounting for the behaviour of the compiler. This task is…

Coding agents and LLM-powered applications routinely send potentially sensitive content to cloud LLM APIs where it may be logged, retained, used for training, or subpoenaed. Existing privacy tooling focuses on network-level encryption and…

This paper describes an `obfuscating' C compiler for encrypted computing. The context consists of (i) a processor that `works encrypted', taking in encrypted inputs and producing encrypted outputs while the data remains in encrypted form…

When implementing secure software, developers must ensure certain requirements, such as the erasure of secret data after its use and execution in real time. Such requirements are not explicitly captured by the C language and could…

The community explored to build private inference frameworks for transformer-based large language models (LLMs) in a server-client setting, where the server holds the model parameters and the client inputs its private data (or prompt) for…

LLM-based code assistants are becoming increasingly popular among developers. These tools help developers improve their coding efficiency and reduce errors by providing real-time suggestions based on the developer's codebase. While…

Formal verification of large C programs is impeded by state-space explosion: Bounded Model Checking (BMC) tools must encode the entire state space up to the predetermined bound by unrolling all nested constructs. We present ConVer, a…

Reducing application runtime, scaling parallel applications to higher numbers of processes/threads, and porting applications to new hardware architectures are tasks necessary in the software development process. Therefore, developers have…

Designing and implementing secure software is inarguably more important than ever. However, despite years of research into privilege separating programs, it remains difficult to actually do so and such efforts can take years of…

The ever-increasing size of open-source Large Language Models (LLMs) renders local deployment impractical for individual users. Decentralized computing has emerged as a cost-effective solution, allowing individuals and small companies to…

Deep learning (DL) compilers are core infrastructure in modern DL systems, offering flexibility and scalability beyond vendor-specific libraries. This work uncovers a fundamental vulnerability in their design: can an official, unmodified…

Deep learning software demands reliability and performance. However, many of the existing deep learning frameworks are software libraries that act as an unsafe DSL in Python and a computation graph interpreter. We present DLVM, a design and…

While large code language models have made significant strides in AI-assisted coding tasks, there are growing concerns about privacy challenges. The user code is transparent to the cloud LLM service provider, inducing risks of unauthorized…

Recent secure code generation methods, using vulnerability-aware fine-tuning, prefix-tuning, and prompt optimization, claim to prevent LLMs from producing insecure code. However, their robustness under adversarial conditions remains…