CyberGym: Evaluating AI Agents’ Cybersecurity Capabilities with Real-World Vulnerabilities at Scale
Authors: Zhun Wang, Tianneng Shi, Jingxuan He, Matthew Cai, Jialin Zhang, Dawn Song | Published: 2025-06-03
Attention Knows Whom to Trust: Attention-based Trust Management for LLM Multi-Agent Systems
Authors: Pengfei He, Zhenwei Dai, Xianfeng Tang, Yue Xing, Hui Liu, Jingying Zeng, Qiankun Peng, Shrivats Agrawal, Samarth Varshney, Suhang Wang, Jiliang Tang, Qi He | Published: 2025-06-03
BitBypass: A New Direction in Jailbreaking Aligned Large Language Models with Bitstream Camouflage
Authors: Kalyan Nakka, Nitesh Saxena | Published: 2025-06-03
A Review of Various Datasets for Machine Learning Algorithm-Based Intrusion Detection System: Advances and Challenges
Authors: Sudhanshu Sekhar Tripathy, Bichitrananda Behera | Published: 2025-06-03
MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models
Authors: Xueqi Cheng, Minxing Zheng, Shixiang Zhu, Yushun Dong | Published: 2025-06-03
IF-GUIDE: Influence Function-Guided Detoxification of LLMs
Authors: Zachary Coalson, Juhan Bae, Nicholas Carlini, Sanghyun Hong | Published: 2025-06-02 | Updated: 2025-06-09
On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective
Authors: Ning Zhang, Henry Kenlay, Li Zhang, Mihai Cucuringu, Xiaowen Dong | Published: 2025-06-01 | Updated: 2025-06-03
A Systematic Review of Metaheuristics-Based and Machine Learning-Driven Intrusion Detection Systems in IoT
Authors: Mohammad Shamim Ahsan, Salekul Islam, Swakkhar Shatabda | Published: 2025-05-31 | Updated: 2025-06-03
A Red Teaming Roadmap Towards System-Level Safety
Authors: Zifan Wang, Christina Q. Knight, Jeremy Kritz, Willow E. Primack, Julian Michael | Published: 2025-05-30 | Updated: 2025-06-09
MCP Safety Training: Learning to Refuse Falsely Benign MCP Exploits using Improved Preference Alignment
Authors: John Halloran | Published: 2025-05-29