Cover Image

Post-Training Local LLM Agents for Linux Privilege Escalation with Verifiable Rewards

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Normann, Philipp, Happe, Andreas, Cito, Jürgen, Arp, Daniel
Format:	Preprint
Published:	2026
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

Enhancing Linux Privilege Escalation Attack Capabilities of Local LLM Agents
by: Probst, Benjamin, et al.
Published: (2026)

LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks
by: Happe, Andreas, et al.
Published: (2023)

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

Got Root? A Linux Priv-Esc Benchmark
by: Happe, Andreas, et al.
Published: (2024)

Cochise: A Reference Harness for Autonomous Penetration Testing
by: Happe, Andreas, et al.
Published: (2026)

Ethics Statements in Autonomous Penetration-Testing Agent Research
by: Happe, Andreas, et al.
Published: (2025)

Prompt Flow Integrity to Prevent Privilege Escalation in LLM Agents
by: Kim, Juhee, et al.
Published: (2025)

Can LLMs Hack Enterprise Networks? -- Replicated Computational Results (RCR) Report
by: Happe, Andreas, et al.
Published: (2026)

On the Surprising Efficacy of LLMs for Penetration-Testing
by: Happe, Andreas, et al.
Published: (2025)

Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks
by: Happe, Andreas, et al.
Published: (2025)

AI-Augmented Ethical Hacking: A Practical Examination of Manual Exploitation and Privilege Escalation in Linux Environments
by: Al-Sinani, Haitham S., et al.
Published: (2024)

Detecting Privilege Escalation in Polyglot Microservices via Agentic Program Analysis
by: Li, Penghui, et al.
Published: (2026)

Progent: Securing AI Agents with Privilege Control
by: Shi, Tianneng, et al.
Published: (2025)

Evaluating Privilege Usage of Agents with Real-World Tools
by: Zhang, Quan, et al.
Published: (2026)

Do Coding Agents Understand Least-Privilege Authorization?
by: Yan, Zheng, et al.
Published: (2026)

BashArena: A Control Setting for Highly Privileged AI Agents
by: Kaufman, Adam, et al.
Published: (2025)

MiniScope: A Least Privilege Framework for Authorizing Tool Calling Agents
by: Zhu, Jinhao, et al.
Published: (2025)

Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward
by: Guo, Weiyang, et al.
Published: (2026)

Agent Privilege Separation in OpenClaw: A Structural Defense Against Prompt Injection
by: Cheng, Darren, et al.
Published: (2026)

Security Risks in Tool-Enabled AI Agents: A Systematic Analysis of Privileged Execution Environments
by: Goel, Hardik
Published: (2026)

VIGIL: Defending LLM Agents Against Tool Stream Injection via Verify-Before-Commit
by: Lin, Junda, et al.
Published: (2026)

Taming Various Privilege Escalation in LLM-Based Agent Systems: A Mandatory Access Control Framework
by: Ji, Zimo, et al.
Published: (2026)

AI-Enhanced Ethical Hacking: A Linux-Focused Experiment
by: Al-Sinani, Haitham S., et al.
Published: (2024)

Detecting Privilege Escalation with Temporal Braid Groups
by: Parisel, Christophe
Published: (2026)

Substituting Proof of Work in Blockchain with Training-Verified Collaborative Model Computation
by: Rafid, Mohammad Ishzaz Asif, et al.
Published: (2025)

LinuxArena: A Control Setting for AI Agents in Live Production Software Environments
by: Tracy, Tyler, et al.
Published: (2026)

Auditing Data Membership in Reinforcement Learning With Verifiable Rewards
by: Liu, Yule, et al.
Published: (2025)

Verifier-Bound Communication for LLM Agents: Certified Bounds on Covert Signaling
by: Tailor, Om
Published: (2026)

IMMACULATE: A Practical LLM Auditing Framework via Verifiable Computation
by: Guo, Yanpei, et al.
Published: (2026)

Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
by: Jamshidi, Saeid, et al.
Published: (2026)

aCAPTCHA: Verifying That an Entity Is a Capable Agent via Asymmetric Hardness
by: Xu, Zuyao, et al.
Published: (2026)

Patch2Vuln: Agentic Reconstruction of Vulnerabilities from Linux Distribution Binary Patches
by: David, Isaac, et al.
Published: (2026)

GPUBreach: Privilege Escalation Attacks on GPUs using Rowhammer
by: Lin, Chris S., et al.
Published: (2026)

LLM Agents can Autonomously Hack Websites
by: Fang, Richard, et al.
Published: (2024)

VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Traces
by: Grigor, Artem, et al.
Published: (2025)

LLM Agents can Autonomously Exploit One-day Vulnerabilities
by: Fang, Richard, et al.
Published: (2024)

CheatAgent: Attacking LLM-Empowered Recommender Systems via LLM Agent
by: Ning, Liang-bo, et al.
Published: (2025)

ESAA-Security: An Event-Sourced, Verifiable Architecture for Agent-Assisted Security Audits of AI-Generated Code
by: Filho, Elzo Brito dos Santos
Published: (2026)

Hybrid Privilege Escalation and Remote Code Execution Exploit Chains
by: Tulla, Miguel, et al.
Published: (2025)

Optimistic Verifiable Training by Controlling Hardware Nondeterminism
by: Srivastava, Megha, et al.
Published: (2024)