相关论文: BlueCodeAgent: A Blue Teaming Agent Enabled by Aut…

Red teaming has evolved from its origins in military applications to become a widely adopted methodology in cybersecurity and AI. In this paper, we take a critical look at the practice of AI red teaming. We argue that despite its current…

Coding agents powered by large language models are becoming central modules of modern IDEs, helping users perform complex tasks by invoking tools. While powerful, tool invocation opens a substantial attack surface. Prior work has…

Foundation model-based agents are increasingly used to automate complex tasks, enhancing efficiency and productivity. However, their access to sensitive resources and autonomous decision-making also introduce significant security risks,…

Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to limited interaction, weak execution grounding, and a lack of…

As cyber threats continue to grow in scale and sophistication, blue team defenders increasingly require advanced tools to proactively detect and mitigate risks. Large Language Models (LLMs) offer promising capabilities for enhancing threat…

Code translation transforms code between programming languages while preserving functionality, which is critical in software development and maintenance. While traditional learning-based code translation methods have limited effectiveness…

Large Language Models (LLMs) have demonstrated considerable potential in improving coding education by providing support for code writing, explanation, and debugging. However, existing LLM-based approaches generally fail to assess students'…

Large Language Models (LLMs) have shown promise in automated code generation but typically excel only in simpler tasks such as generating standalone code units. Real-world software development, however, often involves complex code…

Smart contracts are the backbone of the decentralized web, yet ensuring their functional correctness and security remains a critical challenge. While Large Language Models (LLMs) have shown promise in code generation, they often struggle…

High-quality code documentation is crucial for software development especially in the era of AI. However, generating it automatically using Large Language Models (LLMs) remains challenging, as existing approaches often produce incomplete,…

Frontier large language models (LLMs) are developed by researchers and practitioners with skewed cultural backgrounds and on datasets with skewed sources. However, LLMs' (lack of) multicultural knowledge cannot be effectively assessed with…

Ensuring the safe deployment of AI systems is critical in industry settings where biased outputs can lead to significant operational, reputational, and regulatory risks. Thorough evaluation before deployment is essential to prevent these…

Language Models (LMs) often cannot be deployed because of their potential to harm users in hard-to-predict ways. Prior work identifies harmful behaviors before deployment by using human annotators to hand-write test cases. However, human…

Large Language Model (LLM) Agents have demonstrated remarkable capabilities in task automation and intelligent decision-making, driving the widespread adoption of agent development frameworks such as LangChain and AutoGen. However, these…

Large language models (LLMs) have brought significant advancements to code generation, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like GitHub, introduces…

Large Language Models (LLMs) are set to reshape cybersecurity by augmenting red and blue team operations. Red teams can exploit LLMs to plan attacks, craft phishing content, simulate adversaries, and generate exploit code. Conversely, blue…

Recently, people have suffered from LLM hallucination and have become increasingly aware of the reliability gap of LLMs in open and knowledge-intensive tasks. As a result, they have increasingly turned to search-augmented LLMs to mitigate…

Large language model (LLM) agents are vulnerable to prompt-injection attacks that propagate through multi-step workflows, tool interactions, and persistent context, making input-output filtering alone insufficient for reliable protection.…

As the practicality of Artificial Intelligence (AI) and Machine Learning (ML) based techniques grow, there is an ever increasing threat of adversarial attacks. There is a need to red team this ecosystem to identify system vulnerabilities,…

We introduce a red-teaming methodology that exposes harder-to-catch attacks for coding-agent monitors, suggesting that current practices may under-elicit attacks and overstate monitor performance. We identify three challenges with current…