arXiv:2504.02701
공식 코드 · Papers with Code
Responsible Development of Offensive AI
원문 초록
As AI advances, broader consensus is needed to determine research priorities. This endeavor discusses offensive AI and provides guidance by leveraging Sustainable Development Goals (SDGs) and interpretability techniques. The objective is to more effectively establish priorities that balance societal benefits against risks. The two forms of offensive AI evaluated in this study are vulnerability detection agents, which solve Capture- The-Flag challenges, and AI-powered malware.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Boosting Vulnerability Detection of LLMs via Curriculum Preference Optimization with Synthetic Reasoning Data
SV-TrustEval-C: Evaluating Structure and Semantic Reasoning in Large Language Models for Source Code Vulnerability Analysis
CRAKEN: Cybersecurity LLM Agent with Knowledge-Based Execution
Are Sparse Autoencoders Useful for Java Function Bug Detection?
Can You Really Trust Code Copilots? Evaluating Large Language Models from a Code Security Perspective
Enhancing Large Language Models with Faster Code Preprocessing for Vulnerability Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.