Related papers: Just-in-Time Detection of Silent Security Patches

As Large Language Models (LLMs) scale in size and complexity, the consequences of failures during training become increasingly severe. A major challenge arises from Silent Data Corruption (SDC): hardware-induced faults that bypass…

Open-source software projects are foundational to modern software ecosystems, with the Linux kernel standing out as a critical exemplar due to its ubiquity and complexity. Although security patches are continuously integrated into the Linux…

Defending aligned Large Language Models (LLMs) against jailbreaking attacks is a challenging problem, with existing approaches requiring multiple requests or even queries to auxiliary LLMs, making them computationally heavy. Instead, we…

In today's rapidly evolving technological landscape and advanced software development, the rise in cyber security attacks has become a pressing concern. The integration of robust cyber security defenses has become essential across all…

Large Language Models (LLMs) show significant promise in automating software vulnerability analysis, a critical task given the impact of security failure of modern software systems. However, current approaches in using LLMs to automate…

Code review is a critical practice in software engineering, yet the growing scale and frequency of code patches in modern projects, together with the widespread adoption of AI code assistants, make manual review increasingly challenging.…

As the use of large language models (LLMs) continues to expand, ensuring their safety and robustness has become a critical challenge. In particular, jailbreak attacks that bypass built-in safety mechanisms are increasingly recognized as a…

Large Language Models (LLMs) presents significant priority in text understanding and generation. However, LLMs suffer from the risk of generating harmful contents especially while being employed to applications. There are several black-box…

Open-source large language models (LLMs) have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source codes, model…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks, posing serious safety risks. To address this, existing detection methods either learn attack-specific parameters, which…

The wide deployment of Large Language Models (LLMs) has given rise to strong demands for optimizing their inference performance. Today's techniques serving this purpose primarily focus on reducing latency and improving throughput through…

Large Language Models (LLMs) are being used more and more for various coding tasks, including to help coders identify bugs and are a promising avenue to support coders in various tasks including vulnerability detection -- particularly given…

Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematically evaluates the security comprehension of five leading LLMs: GPT-4o-Mini,…

With LLMs increasingly deployed in corporate data management, it is crucial to ensure that these models do not leak sensitive information. In the context of corporate data management, the concept of sensitivity awareness has been…

Warning: This paper contains examples of harmful language, and reader discretion is recommended. The increasing open release of powerful large language models (LLMs) has facilitated the development of downstream applications by reducing the…

Large language models deployed at runtime can misbehave in ways that clean-data validation cannot anticipate: training-time backdoors lie dormant until triggered, jailbreaks subvert safety alignment, and prompt injections override the…

Automating software vulnerability detection (SVD) remains a critical challenge in an era of increasingly complex and interdependent software systems. Despite significant advances in Large Language Models (LLMs) for code analysis, prevailing…

Prompt injection attacks have become an increasing vulnerability for LLM applications, where adversarial prompts exploit indirect input channels such as emails or user-generated content to circumvent alignment safeguards and induce harmful…

Public development processes are a key characteristic of open source projects. However, fixes for vulnerabilities are usually discussed privately among a small group of trusted maintainers, and integrated without prior public involvement.…

Despite extensive alignment efforts, Large Vision-Language Models (LVLMs) remain vulnerable to jailbreak attacks. To mitigate these risks, existing detection methods are essential, yet they face two major challenges: generalization and…