Introduces the first open multi-host cyber range benchmark AgentCyberRange with Cage toolchain and evaluates six frontier AI systems on web exploitation and post-exploitation tasks across 110 vulnerabilities.
hub Mixed citations
LLM Agents can Autonomously Exploit One-day Vulnerabilities
Mixed citation behavior. Most common role is background (60%).
34
Pith papers citing it
Background
60% of classified citations
abstract
LLMs have becoming increasingly powerful, both in their benign and malicious uses. With the increase in capabilities, researchers have been increasingly interested in their ability to exploit cybersecurity vulnerabilities. In particular, recent work has conducted preliminary studies on the ability of LLM agents to autonomously hack websites. However, these studies are limited to simple vulnerabilities. In this work, we show that LLM agents can autonomously exploit one-day vulnerabilities in real-world systems. To show this, we collected a dataset of 15 one-day vulnerabilities that include ones categorized as critical severity in the CVE description. When given the CVE description, GPT-4 is capable of exploiting 87% of these vulnerabilities compared to 0% for every other model we test (GPT-3.5, open-source LLMs) and open-source vulnerability scanners (ZAP and Metasploit). Fortunately, our GPT-4 agent requires the CVE description for high performance: without the description, GPT-4 can exploit only 7% of the vulnerabilities. Our findings raise questions around the widespread deployment of highly capable LLM agents.
hub tools
citation-role summary
background 8
method 1
other 1
citation-polarity summary
representative citing papers
APIOT is the first LLM framework to complete the full autonomous discovery-to-remediation cycle on bare-metal OT devices, reaching 90% success across 290 runs on Zephyr RTOS.
A decoupled evaluation framework shows LLM penetration agents reach 90% exploitation success with ground-truth context but only 50% reconnaissance recall due to telemetry parsing failures across 50 vulnerabilities.
LLM agents exhibit persistent attack-selection biases as fixed traits independent of success rates, with a bias momentum effect that resists steering and yields no performance gain.
SLYP agentic pipeline discovers race condition vulnerabilities in Windows COM binaries and generates debugger-verified PoCs, scoring 0.973 F1 on a 40-case benchmark and finding 28 new confirmed vulnerabilities in production services.
PHANTOM raises honeytoken believability from 0.576 to 0.778 by adding organization-specific mimicry, lifting human acceptance to 100% and detection resistance to 0.870.
A new 7x4 taxonomy organizes agentic AI security threats by architectural layer and persistence timescale, revealing under-explored upper layers and missing defenses after surveying 116 papers.
LLMVD.js uses LLM agents to confirm 84% of taint-style vulnerabilities on public benchmarks (vs. <22% for prior tools) and generates validated exploits for 36 of 260 new packages (vs. ≤2 for traditional tools).
A systematization of knowledge paper that taxonomizes honeypot detection vectors, synthesizes LLM-honeypot literature into canonical architecture and evaluation methods, and proposes a roadmap for autonomous deception systems.
Chai uses AI to enhance differential testing for cryptographic misuse, cataloging library-level flaws and propagating them to find over 100 vulnerabilities including a critical one in a widely deployed SSL library.
LLMs fall for deceptive traps at higher rates than humans, lack the human attention-diversion effect, and exploit traps 73.4% of the time even after recognizing them in reasoning.
APT-Agent automates penetration testing with LLMs using rectification and memory modules, achieving 84.29% end-to-end success on Metasploitable 2 versus lower rates for baselines.
uGen is the first retrieval-augmented multi-agent LLM framework for generating functionally correct microarchitectural attack PoCs, reporting up to 100% success on Spectre-v1 and 80% on Prime+Probe at low cost.
An agentic pipeline localizes the security-relevant function in 10 of 20 Ubuntu binary security updates and produces an accepted root-cause classification in 11 of 20, limited mainly by binary differencing coverage.
Empirical comparison of agentic topologies for offensive security shows MAS-Indep reaching 64.2% validated detection while simpler baselines remain competitive on efficiency, with whitebox and web targets outperforming blackbox and binary ones.
Kimi K2.5 matches closed models on dual-use tasks but refuses fewer CBRNE requests and shows some sabotage and self-replication tendencies.
RSA prompting enables LLMs to automatically create functional exploits for CVEs in Odoo ERP, succeeding on all tested cases in 3-5 rounds and removing the need for manual effort.
Autonomous AI cyber systems deployed by civilians fail the one-causal-step and integral-part requirements of the IHL direct participation test because harm arises from post-disengagement system decisions.
OpenAnt is an open-source pipeline that uses code decomposition, LLM-based adversarial verification, and automated dynamic testing to find vulnerabilities in large projects like OpenSSL and WordPress while claiming lower false positives.
Proposes demand-driven, tenant-local derivation of CSPM rules from catalogue-asset intersections to eliminate vendor rule authoring and release cadence delays.
FORGE deploys a fixed five-agent pipeline on 603 CVEs to achieve 67.8% L1+ exploitation success at $1.50 per CVE while generating detection rules whose grounding improves with deeper exploitation traces.
Analysis of 67,453 OpenClaw skills shows three scanners overlap on at most 10.4% of combined positives, with 81.9% flagged by only one scanner and distinct profiles for malicious versus suspicious skills.
Vulnsage, a multi-agent framework, generates 34.64% more exploits than prior tools and verified 146 zero-day vulnerabilities in real-world open-source libraries.
xOffense automates penetration testing via a fine-tuned Qwen3-32B LLM in a multi-agent setup with specialized agents for reconnaissance, vulnerability scanning, and exploitation, reporting 79.17% sub-task completion on AutoPenBench and AI-Pentest-Benchmark.
citing papers explorer
-
Large Language Model-Based Agents for Software Engineering: A Survey
A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.