Image de couverture de livre

Cyber-Zero: Training Cybersecurity Agents without Runtime

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zhuo, Terry Yue, Wang, Dingmin, Ding, Hantian, Kumar, Varun, Wang, Zijian
Format:	Preprint
Publié:	2025
Sujets:	Cryptography and Security Computation and Language Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Training Language Model Agents to Find Vulnerabilities with CTF-Dojo
par: Zhuo, Terry Yue, et autres
Publié: (2025)

Cyber-Attack Technique Classification Using Two-Stage Trained Large Language Models
par: You, Weiqiu, et autres
Publié: (2024)

Image Hijacks: Adversarial Images can Control Generative Models at Runtime
par: Bailey, Luke, et autres
Publié: (2023)

ThreatCrawl: A BERT-based Focused Crawler for the Cybersecurity Domain
par: Kuehn, Philipp, et autres
Publié: (2023)

Evaluation of LLM Chatbots for OSINT-based Cyber Threat Awareness
par: Shafee, Samaneh, et autres
Publié: (2024)

BountyBench: Dollar Impact of AI Agent Attackers and Defenders on Real-World Cybersecurity Systems
par: Zhang, Andy K., et autres
Publié: (2025)

SecFormer: Fast and Accurate Privacy-Preserving Inference for Transformer Models via SMPC
par: Luo, Jinglong, et autres
Publié: (2024)

Automated CVE Analysis: Harnessing Machine Learning In Designing Question-Answering Models For Cybersecurity Information Extraction
par: Faruk, Tanjim Bin
Publié: (2024)

AgentArmor: Enforcing Program Analysis on Agent Runtime Trace to Defend Against Prompt Injection
par: Wang, Peiran, et autres
Publié: (2025)

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
par: Wang, Fei, et autres
Publié: (2025)

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
par: Wang, Zhun, et autres
Publié: (2025)

Digger: Detecting Copyright Content Mis-usage in Large Language Model Training
par: Li, Haodong, et autres
Publié: (2024)

A Robust Cybersecurity Topic Classification Tool
par: Pelofske, Elijah, et autres
Publié: (2021)

Large Language Models in Cybersecurity: State-of-the-Art
par: Motlagh, Farzad Nourmohammadzadeh, et autres
Publié: (2024)

A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment
par: Wang, Kun, et autres
Publié: (2025)

AutoDefense: Multi-Agent LLM Defense against Jailbreak Attacks
par: Zeng, Yifan, et autres
Publié: (2024)

Intrinsic Fingerprint of LLMs: Continue Training is NOT All You Need to Steal A Model!
par: Yoon, Do-hyeon, et autres
Publié: (2025)

Can Federated Learning Safeguard Private Data in LLM Training? Vulnerabilities, Attacks, and Defense Evaluation
par: Guo, Wenkai, et autres
Publié: (2025)

RLShield: Practical Multi-Agent RL for Financial Cyber Defense with Attack-Surface MDPs and Real-Time Response Orchestration
par: Nayak, Srikumar
Publié: (2026)

Tuning without Peeking: Provable Generalization Bounds and Robust LLM Post-Training
par: Labiad, Ismail, et autres
Publié: (2025)

AirGapAgent: Protecting Privacy-Conscious Conversational Agents
par: Bagdasarian, Eugene, et autres
Publié: (2024)

Transferable Embedding Inversion Attack: Uncovering Privacy Risks in Text Embeddings without Model Queries
par: Huang, Yu-Hsiang, et autres
Publié: (2024)

Jailbreak-Zero: A Path to Pareto Optimal Red Teaming for Large Language Models
par: Hu, Kai, et autres
Publié: (2025)

PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Prompts
par: Zhu, Kaijie, et autres
Publié: (2023)

AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
par: Li, Tung-Ling, et autres
Publié: (2025)

The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions
par: Wallace, Eric, et autres
Publié: (2024)

Adversarial Data Poisoning for Fake News Detection: How to Make a Model Misclassify a Target News without Modifying It
par: Siciliano, Federico, et autres
Publié: (2023)

CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models
par: Bhatt, Manish, et autres
Publié: (2024)

LLM Cyber Evaluations Don't Capture Real-World Risk
par: Lukošiūtė, Kamilė, et autres
Publié: (2025)

Can We Infer Confidential Properties of Training Data from LLMs?
par: Huang, Pengrun, et autres
Publié: (2025)

Contextual Agent Security: A Policy for Every Purpose
par: Tsai, Lillian, et autres
Publié: (2025)

Assessing Deanonymization Risks with Stylometry-Assisted LLM Agent
par: Zhang, Boyang, et autres
Publié: (2026)

To Defend Against Cyber Attacks, We Must Teach AI Agents to Hack
par: Zhuo, Terry Yue, et autres
Publié: (2026)

Tracing Privacy Leakage of Language Models to Training Data via Adjusted Influence Functions
par: Liu, Jinxin, et autres
Publié: (2024)

BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents
par: Wang, Yifei, et autres
Publié: (2024)

Learning from Negative Examples: Why Warning-Framed Training Data Teaches What It Warns Against
par: Enkhbayar, Tsogt-Ochir
Publié: (2025)

A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models
par: Dang, Cuong, et autres
Publié: (2024)

AutoMalDesc: Large-Scale Script Analysis for Cyber Threat Research
par: Apostu, Alexandru-Mihai, et autres
Publié: (2025)

WARDEN: Multi-Directional Backdoor Watermarks for Embedding-as-a-Service Copyright Protection
par: Shetty, Anudeex, et autres
Publié: (2024)

When Routine Chats Turn Toxic: Unintended Long-Term State Poisoning in Personalized Agents
par: Xu, Xiaoyu, et autres
Publié: (2026)