Cover Image

ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Zhun, Schiller, Nico, Li, Hongwei, Narayana, Srijiith Sesha, Nasr, Milad, Carlini, Nicholas, Qi, Xiangyu, Wallace, Eric, Bursztein, Elie, Invernizzi, Luca, Thomas, Kurt, Shoshitaishvili, Yan, Guo, Wenbo, He, Jingxuan, Holz, Thorsten, Song, Dawn
Format:	Preprint
Published:	2026
Subjects:	Cryptography and Security Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial Attacks
by: Nasr, Milad, et al.
Published: (2025)

Remote Timing Attacks on Efficient Language Model Inference
by: Carlini, Nicholas, et al.
Published: (2024)

CyberGym: Evaluating AI Agents' Real-World Cybersecurity Capabilities at Scale
by: Wang, Zhun, et al.
Published: (2025)

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

Generalized Power Attacks against Crypto Hardware using Long-Range Deep Learning
by: Bursztein, Elie, et al.
Published: (2023)

VulnLLM-R: Specialized Reasoning LLM with Agent Scaffold for Vulnerability Detection
by: Nie, Yuzhou, et al.
Published: (2025)

Query-Based Adversarial Prompt Generation
by: Hayase, Jonathan, et al.
Published: (2024)

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses
by: Carlini, Nicholas, et al.
Published: (2025)

Frontier AI's Impact on the Cybersecurity Landscape
by: Potter, Yujin, et al.
Published: (2025)

Magika: AI-Powered Content-Type Detection
by: Fratantonio, Yanick, et al.
Published: (2024)

RETVec: Resilient and Efficient Text Vectorizer
by: Bursztein, Elie, et al.
Published: (2023)

Avoiding Generative Model Writer's Block With Embedding Nudging
by: Zand, Ali, et al.
Published: (2024)

Video-Native Koopman Operator Learning for Active Wildfire Risk Mapping
by: Achyuta, Sesha
Published: (2025)

VictualMark™: Building a Verified, Physics-Backed Food Economy on Top of DataCulture, 512TD, BRIXBOX, and NutriBox
by: Achyuta, Sesha
Published: (2025)

Privacy Side Channels in Machine Learning Systems
by: Debenedetti, Edoardo, et al.
Published: (2023)

Gym-Anything: Turn any Software into an Agent Environment
by: Aggarwal, Pranjal, et al.
Published: (2026)

Pattern Enhanced Multi-Turn Jailbreaking: Exploiting Structural Vulnerabilities in Large Language Models
by: Nihal, Ragib Amin, et al.
Published: (2025)

AbideGym: Turning Static RL Worlds into Adaptive Challenges
by: Aryan, Abi, et al.
Published: (2025)

DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle
by: Tang, Yuheng, et al.
Published: (2026)

A Framework for Formalizing LLM Agent Security
by: Siu, Vincent, et al.
Published: (2026)

TOWARDS GOOD GOVERNANCE: E-GOVERNANCE AS A CATALYST FOR SUSTAINABLE DEVELOPMENT
by: A Sesha Reddy
Published: (2023)

DarthShader: Fuzzing WebGPU Shader Translators & Compilers
by: Bernhard, Lukas, et al.
Published: (2024)

No Peer, no Cry: Network Application Fuzzing via Fault Injection
by: Bars, Nils, et al.
Published: (2024)

An Explorative Study of Pig Butchering Scams
by: Acharya, Bhupendra, et al.
Published: (2024)

Bad Neighbors: On Understanding VPN Provider Networks
by: Rytilahti, Teemu, et al.
Published: (2024)

DROIDCCT: Cryptographic Compliance Test via Trillion-Scale Measurement
by: Moghimi, Daniel, et al.
Published: (2026)

Profiling Resilient to Change in Probe Position
by: Bursztein, Elie, et al.
Published: (2026)

OpenSage: Self-programming Agent Generation Engine
by: Li, Hongwei, et al.
Published: (2026)

ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases
by: Zhong, Ziqian, et al.
Published: (2025)

Kelvin and Easterly Wave Interactions and Their Modulation by Diurnal Cycle over Eastern Atlantic and Tropical Africa
by: Mantripragada, Rama Sesha Sridhar
Published: (2021)

Anota: Identifying Business Logic Vulnerabilities via Annotation-Based Sanitization
by: Wang, Meng, et al.
Published: (2025)

The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey
by: Kim, Juhee, et al.
Published: (2026)

LeakAgent: RL-based Red-teaming Agent for LLM Privacy Leakage
by: Nie, Yuzhou, et al.
Published: (2024)

Exploiting LLM Quantization
by: Egashira, Kazuki, et al.
Published: (2024)

PoC-Gym: Towards More Reliable LLM-Assisted Proof-of-Concept Exploit Generation
by: Gezgin, Derin, et al.
Published: (2026)

Isabel Sarli camaleónica. Hibridaciones entre gender y genre en las coproducciones latinoamericanas de la dupla con Armando Bó
by: Agostina Invernizzi
Published: (2025)

NANOTECNOLOGÍA EN LOS MEDIOS: ¿QUÉ INFORMACIÓN LLEGA AL PÚBLICO?
by: Noela Invernizzi
Published: (2009)

PRESENTACIÓN DE LOS LIBROS SINFONÍA DE LA ARMONÍA DE LAS REVELACIONES CELESTIALES DE HILDEGARD DE BINGEN Y THE VOICE OF SILENCE
by: Lucía Invernizzi
Published: (2005)

El despegue de las nanotecnologías
by: Noela Invernizzi
Published: (2005)

Niños y adolescentes trabajadores en las calles de Lima: vida cotidiana y estrategias familiares de supervivencia
by: Antonella Invernizzi
Published: (2014)