Cover Image

Dynamic Risk Assessments for Offensive Cybersecurity Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Boyi, Stroebl, Benedikt, Xu, Jiacen, Zhang, Joie, Li, Zhou, Henderson, Peter
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

A Survey on Offensive AI Within Cybersecurity
by: Girhepuje, Sahil, et al.
Published: (2024)

Weaponizing Language Models for Cybersecurity Offensive Operations: Automating Vulnerability Assessment Report Validation; A Review Paper
by: Almuhaidib, Abdulrahman S, et al.
Published: (2025)

Artificial Intelligence as the New Hacker: Developing Agents for Offensive Security
by: Valencia, Leroy Jacob
Published: (2024)

D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security
by: Udeshi, Meet, et al.
Published: (2025)

CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly
by: Fan, Yihe, et al.
Published: (2026)

AutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
by: Xu, Jiacen, et al.
Published: (2024)

Poster: SpiderSim: Multi-Agent Driven Theoretical Cybersecurity Simulation for Industrial Digitalization
by: Li, Jiaqi, et al.
Published: (2025)

Semantic Labeling for Third-Party Cybersecurity Risk Assessment: A Semi-Supervised Approach to Intent-Aware Question Retrieval
by: Eldin, Ali Nour, et al.
Published: (2026)

Offensive Security for AI Systems: Concepts, Practices, and Applications
by: Harguess, Josh, et al.
Published: (2025)

Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark
by: Shao, Minghao, et al.
Published: (2025)

On Evaluating the Durability of Safeguards for Open-Weight LLMs
by: Qi, Xiangyu, et al.
Published: (2024)

OCCULT: Evaluating Large Language Models for Offensive Cyber Operation Capabilities
by: Kouremetis, Michael, et al.
Published: (2025)

ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents
by: Lee, Seunghyun, et al.
Published: (2026)

Emerging Cyber Attack Risks of Medical AI Agents
by: Qiu, Jianing, et al.
Published: (2025)

Offensive Robot Cybersecurity
by: Mayoral-Vilches, Víctor
Published: (2025)

AI-Driven Cybersecurity Threats: A Survey of Emerging Risks and Defensive Strategies
by: Erukude, Sai Teja, et al.
Published: (2026)

Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design
by: Happe, Andreas, et al.
Published: (2025)

SecMate: Multi-Agent Adaptive Cybersecurity Troubleshooting with Tri-Context Personalization
by: Meidan, Yair, et al.
Published: (2026)

The Human-Machine Identity Blur: A Unified Framework for Cybersecurity Risk Management in 2025
by: Janani, Kush
Published: (2025)

CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking
by: Rani, Nanda, et al.
Published: (2026)

From Beats to Breaches:How Offensive AI Infers Sensitive User Information from Playlists
by: Cecconello, Stefano, et al.
Published: (2026)

A Cybersecurity Risk Analysis Framework for Systems with Artificial Intelligence Components
by: Camacho, Jose Manuel, et al.
Published: (2024)

Adversarial Reinforcement Learning for Offensive and Defensive Agents in a Simulated Zero-Sum Network Environment
by: Shahid, Abrar, et al.
Published: (2025)

Integrative Approaches in Cybersecurity and AI
by: Omar, Marwan
Published: (2024)

Best Practices for Biorisk Evaluations on Open-Weight Bio-Foundation Models
by: Wei, Boyi, et al.
Published: (2025)

Leveraging Large Language Models for Cybersecurity Risk Assessment -- A Case from Forestry Cyber-Physical Systems
by: Gultekin, Fikret Mert, et al.
Published: (2025)

A Comparative Evaluation of AI Agent Security Guardrails
by: Li, Qi, et al.
Published: (2026)

Neuro-Symbolic AI for Cybersecurity: State of the Art, Challenges, and Opportunities
by: Hakim, Safayat Bin, et al.
Published: (2025)

Fundamental Risks in the Current Deployment of General-Purpose AI Models: What Have We (Not) Learnt From Cybersecurity?
by: Fritz, Mario
Published: (2024)

AI Risk Management Should Incorporate Both Safety and Security
by: Qi, Xiangyu, et al.
Published: (2024)

When LLMs Meet Cybersecurity: A Systematic Literature Review
by: Zhang, Jie, et al.
Published: (2024)

An Adversarial Perspective on Machine Unlearning for AI Safety
by: Łucki, Jakub, et al.
Published: (2024)

From Texts to Shields: Convergence of Large Language Models and Cybersecurity
by: Li, Tao, et al.
Published: (2025)

Crimson: Empowering Strategic Reasoning in Cybersecurity through Large Language Models
by: Jin, Jiandong, et al.
Published: (2024)

DemonAgent: Dynamically Encrypted Multi-Backdoor Implantation Attack on LLM-based Agent
by: Zhu, Pengyu, et al.
Published: (2025)

AgenticCyber: A GenAI-Powered Multi-Agent System for Multimodal Threat Detection and Adaptive Response in Cybersecurity
by: Roy, Shovan
Published: (2025)

AgentSys: Secure and Dynamic LLM Agents Through Explicit Hierarchical Memory Management
by: Wen, Ruoyao, et al.
Published: (2026)

Reinforcement Learning for Automated Cybersecurity Penetration Testing
by: López-Montero, Daniel, et al.
Published: (2025)

A Survey of Large Language Models in Cybersecurity
by: da Silva, Gabriel de Jesus Coelho, et al.
Published: (2024)

AgentMark: Utility-Preserving Behavioral Watermarking for Agents
by: Huang, Kaibo, et al.
Published: (2026)