相关论文: SoK: Understanding (New) Security Issues Across AI…

The AI Control research agenda aims to develop control protocols: safety techniques that prevent untrusted AI systems from taking harmful actions during deployment. Because human oversight is expensive, one approach is trusted monitoring,…

AI-supported programming has arrived, as shown by the introduction and successes of large language models for code, such as Copilot/Codex (Github/OpenAI) and AlphaCode (DeepMind). Above human average performance on programming challenges is…

Problem Space: AI Vulnerabilities and Quantum Threats Generative AI vulnerabilities: model inversion, data poisoning, adversarial inputs. Quantum threats Shor Algorithm breaking RSA ECC encryption. Challenge Secure generative AI models…

Audio watermarking is increasingly used to verify the provenance of AI-generated content, enabling applications such as detecting AI-generated speech, protecting music IP, and defending against voice cloning. To be effective, audio…

With the rapid development of large language models in code generation, AI-powered editors such as GitHub Copilot and Cursor are revolutionizing software development practices. At the same time, studies have identified potential defects in…

Today's Internet utilizes a multitude of different protocols. While some of these protocols were first implemented and used and later documented, other were first specified and then implemented. Regardless of how protocols came to be, their…

Teaching Computer Science (CS) students how to comprehend and maintain legacy code bases is a critical challenge in software engineering education. While Generative AI (GenAI) assistants like GitHub Copilot improve task completion speed and…

Modern software relies on a multitude of automated testing and quality assurance tools to prevent errors, bugs and potential vulnerabilities. This study sets out to provide a head-to-head, quantitative and qualitative evaluation of six…

Large language models (LLMs) used across enterprises often use proprietary models and operate on sensitive inputs and data. The wide range of attack vectors identified in prior research - targeting various software and hardware components…

The idea of applying machine learning(ML) to solve problems in security domains is almost 3 decades old. As information and communications grow more ubiquitous and more data become available, many security risks arise as well as appetite to…

Background: AI-powered code generation, fueled by Large Language Models (LLMs), is revolutionizing software development. Models like OpenAI's Codex and GPT-4, alongside DeepSeek, leverage vast code and natural language datasets. However,…

Software vulnerabilities continue to be the primary cause of cyberattacks. It is crucial to identify vulnerabilities in applications' source code before attackers gain access to them and exploit any vulnerability they may contain.…

AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210 safety benchmarks that maps out common challenges in safety…

AI-driven software development has rapidly advanced with the emergence of software development agents that leverage large language models (LLMs) to tackle complex, repository-level software engineering tasks. These agents go beyond just…

With the advent of decentralised digital currencies powered by blockchain technology, a new era of peer-to-peer transactions has commenced. The rapid growth of the cryptocurrency economy has led to increased use of transaction-enabling…

The increasing prevalence of software vulnerabilities necessitates automated vulnerability repair (AVR) techniques. This Systematization of Knowledge (SoK) provides a comprehensive overview of the AVR landscape, encompassing both synthetic…

In recent years, large language models have been responsible for great advances in the field of artificial intelligence (AI). ChatGPT in particular, an AI chatbot developed and recently released by OpenAI, has taken the field to the next…

This paper aims to explore fundamental questions in the era when AI coding assistants like GitHub Copilot are widely adopted: what do developers truly value and criticize in AI coding assistants, and what does this reveal about their needs…

What makes safety claims about general purpose AI systems such as large language models trustworthy? We show that rather than the capabilities of security tools such as alignment and red teaming procedures, it is security practices based on…

Our everyday lives now heavily rely on artificial intelligence (AI) powered large language models (LLMs). Like regular users, programmers are also benefiting from the newest large language models. In response to the critical role that AI…