Related papers: WaDec: Decompiling WebAssembly Using Large Languag…

Large Language Models (LLMs) have demonstrated remarkable capabilities across a variety of software engineering and coding tasks. However, their application in the domain of code and compiler optimization remains underexplored. Training…

Large Language Models (LLMs) prompted to generate chain-of-thought (CoT) exhibit impressive reasoning capabilities. Recent attempts at prompt decomposition toward solving complex, multi-step reasoning problems depend on the ability of the…

Superoptimization is the task of transforming a program into a faster one while preserving its input-output behavior. In this work, we investigate whether large language models (LLMs) can serve as superoptimizers, generating assembly…

Assembly code search is vital for reducing the burden on reverse engineers, allowing them to quickly identify specific functions using natural language within vast binary programs. Despite its significance, this critical task is impeded by…

Cloud computing requires isolation and portability for workloads. Cloud vendors must isolate each user's resources from others to prevent them from attacking other users or the whole system. Users may want to move their applications to…

We describe Swivel, a new compiler framework for hardening WebAssembly (Wasm) against Spectre attacks. Outside the browser, Wasm has become a popular lightweight, in-process sandbox and is, for example, used in production to isolate…

There is an explosive growth of information in the World Wide Web thus posing a challenge to Web users to extract essential knowledge from the Web. Search engines help us to narrow down the search in the form of Search Engine Result Pages…

Binary code analysis is the foundation of crucial tasks in the security domain; thus building effective binary analysis techniques is more important than ever. Large language models (LLMs) although have brought impressive improvement to…

In this paper we wish to introduce a method to reconstruct large size Welch Bound Equality (WBE) codes from small size WBE codes. The advantage of these codes is that the implementation of ML decoder for the large size codes is reduced to…

Wasm is gaining popularity outside the Web as a well-specified low-level binary format with ISA portability, low memory footprint and polyglot targetability, enabling efficient in-process sandboxing of untrusted code. Despite these…

Large Language Models (LLMs) have exhibited significant proficiency in code debugging, especially in automatic program repair, which may substantially reduce the time consumption of developers and enhance their efficiency. Significant…

Quantization of Large Language Models (LLMs) has recently gained popularity, particularly for on-device settings with limited hardware resources. While efficient, quantization inevitably degrades model quality, especially in aggressive…

Progress in machine learning has been driven in large part by massive increases in data. However, large web-scale datasets such as LAION are largely uncurated beyond searches for exact duplicates, potentially leaving much redundancy. Here,…

Large Language Models (LLMs) typically excel at coding tasks involving high-level programming languages, as opposed to lower-level programming languages, such as assembly. We propose a synthetic data generation method named C-ing Clearly,…

Autoregressive (AR) generation is the standard decoding paradigm for Large Language Models (LLMs), but its token-by-token nature limits parallelism at inference time. Diffusion Language Models (DLLMs) offer parallel decoding by recovering…

The goal of decompilation is to convert compiled low-level code (e.g., assembly code) back into high-level programming languages, enabling analysis in scenarios where source code is unavailable. This task supports various reverse…

Instruction-following has emerged as a crucial capability for large language models (LLMs). However, existing approaches often rely on pre-existing documents or external resources to synthesize instruction-following data, which limits their…

Automatically generating webpage code from webpage designs can significantly reduce the workload of front-end developers, and recent Multimodal Large Language Models (MLLMs) have shown promising potential in this area. However, our…

Advancements in large language models (LLMs) have unlocked remarkable capabilities. While deploying these models typically requires server-grade GPUs and cloud-based inference, the recent emergence of smaller open-source models and…

Large language models (LLMs) exhibit remarkable capabilities across diverse tasks, yet aligning them efficiently and effectively with human expectations remains a critical challenge. This thesis advances LLM alignment by introducing novel…