홈 › Papers

RAVEN: Retrieval-Augmented Vulnerability Exploration Network for Memory Corruption Analysis in User Code and Binary Programs

2026-04-20 · Parteek Jamwal, Minghao Shao, Boyuan Chen, Achyuta Muthuvelan, Asini Subanya, Boubacar Ballo, Kashish Satija, Mariam Shafey, Mohamed Mahmoud, Moncif Dahaji Bouffi, Pasindu Wickramasinghe, Siyona Goel, Yaakulya Sabbani, Hakim Hacid, Mthandazo Ndhlovu, Eleanna Kafeza, Sanjay Rawat, Muhammad Shafique arxiv

Large Language Models (LLMs) have demonstrated remarkable capabilities across various cybersecurity tasks, including vulnerability classification, detection, and patching. However, their potential in automated vulnerability report documentation and analysis remains underexplored. We present RAVEN (Retrieval Augmented Vulnerability Exploration Network), a framework leveraging LLM agents and Retrieval Augmented Generation (RAG) to synthesize comprehensive vulnerability analysis reports. Given vulnerable source code, RAVEN generates reports following the Google Project Zero Root Cause Analysis template. The framework uses four modules: an Explorer agent for vulnerability identification, a RAG engine retrieving relevant knowledge from curated databases including Google Project Zero reports and CWE entries, an Analyst agent for impact and exploitation assessment, and a Reporter agent for structured report generation. To ensure quality, RAVEN includes a task specific LLM Judge evaluating reports across structural integrity, ground truth alignment, code reasoning quality, and remediation quality. We evaluate RAVEN on 105 vulnerable code samples covering 15 CWE types from the NIST-SARD dataset. Results show an average quality score of 54.21%, supporting the effectiveness of our approach for automated vulnerability documentation.

📄 PDF Abstract BibTeX arXiv:2604.17948

Code (0)

등록된 구현이 없습니다.

RAVEN: Agentic RAG for Automated Vulnerability Repair

2026-06-21 · Varun Gadey, Zijie Liu, Alexandra Dmitrienko arxiv

Automated vulnerability repair has emerged as a promising direction to mitigate the growing number of software vulnerabilities. Recent advances in Large Language Models (LLMs) have further accelerated research in automat…

RAVENEA: A Benchmark for Multimodal Retrieval-Augmented Visual Culture Understanding

2025-05-20 · Jiaang Li, Yifei Yuan, Wenyan Li, Mohammad Aliannejadi 외

As vision-language models (VLMs) become increasingly integrated into daily life, the need for accurate visual culture understanding is becoming critical. Yet, these models frequently fall short in interpreting cultural n…

Image Captioning Question Answering RAG Retrieval+2

RAVEN: Long-Horizon Reasoning & Navigation with a Visuo-Spatio-Temporal Memory

2026-06-23 · Yixun Hu, Zhicheng Zheng, Lihan Zha, Chunwei Xing 외 arxiv

Long-term robot deployment requires a compact and scalable memory that preserves fine-grained visual semantics, grounds observations in space and time, and enables efficient storage and retrieval. In this paper, we propo…

Question Answering

ER-MIA: Black-Box Adversarial Memory Injection Attacks on Long-Term Memory-Augmented Large Language Models

2026-02-17 · Mitchell Piehl, Zhaohan Xi, Zuobin Xiong, Pan He 외 arxiv

Large language models (LLMs) are increasingly augmented with long-term memory systems to overcome finite context windows and enable persistent reasoning across interactions. However, recent research finds that LLMs becom…

RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models

2023-08-15 · Jie Huang, Wei Ping, Peng Xu, Mohammad Shoeybi 외

In this paper, we investigate the in-context learning ability of retrieval-augmented encoder-decoder language models. We first conduct a comprehensive analysis of existing models and identify their limitations in in-cont…

Decoder In-Context Learning Language Modeling Language Modelling+3