Tagged articles
vulnerability research
15 articles · Page 1 of 1
Renowned security researcher Yuki Chen joins Zhipu AI and demonstrates using the GLM model to discover Windows vulnerabilities, earning 23 Microsoft MSRC acknowledgments; NIST and Anthropic benchmarks show GLM-5.3 leads open-weight models in cybersecurity tasks but trails frontier models by about four months.
Anthropic ExploitBenchGLMMicrosoft MSRC
0 likes · 8 min read

TencentOS's Corvus AI discovered three previously unknown kernel vulnerabilities, including XFSTango (CVE-2026-80530), within 72 hours of a known vulnerability disclosure, demonstrating proactive AI-driven vulnerability hunting across multiple Linux distributions.
AI-assisted securityCVE-2026-80530Corvus AI
0 likes · 18 min read

Sangfor’s security‑focused AI, built on the domestic GLM‑5.2 model, completed 1,301 of 1,507 real‑world vulnerability tasks in the CyberGym benchmark, achieving an 86.3% success rate that places it among the global top‑four and demonstrates how evidence‑governed multi‑agent systems can turn model capabilities into verifiable security outcomes.
AI securityCyberGymEvidence governance
0 likes · 10 min read

A Korean security student built a three‑stage LLM workflow that separates discovery, semi‑filtering, and final verification, enabling the automated discovery of more than ten real 0‑day vulnerabilities in popular open‑source projects such as Grafana, Nextcloud, and Matomo.
AI securityCVEGrafana
0 likes · 12 min read

The local‑vuln‑research‑pipeline, built around the 14B Qwen2.5‑Coder model, combines a deterministic code‑graph with LLM‑driven exploitability reasoning to exhaustively enumerate source‑to‑sink paths across multiple languages, offering detailed reports while running entirely on local hardware.
LLM auditingQwen2.5-Codercode graph
0 likes · 9 min read

DeepZero is an open‑source, high‑concurrency pipeline engine that lets security researchers define end‑to‑end vulnerability analysis workflows in YAML, orchestrating tools like Ghidra, Semgrep and large language models, while providing parallel execution, state persistence and automatic recovery.
DeepZeroGhidraLLM
0 likes · 10 min read

The article demonstrates that vulnerability discovery depends on a flexible orchestration harness rather than on exclusive frontier LLMs, using the open‑source IronCurtain framework with commercial and open‑weight models to reproduce a 27‑year‑old OpenBSD bug and uncover new zero‑day flaws in widely used projects, while analysing costs, workflow design, and security implications.
AI orchestrationIronCurtainLLM security
0 likes · 13 min read

The article argues that the bottleneck in security research is information scarcity, not talent, and introduces Preview—a RAG platform that indexes recent write‑ups and provides a simple API allowing AI agents to retrieve up‑to‑date vulnerability details, overcoming frozen LLM knowledge and delivering raw source links for accurate exploitation.
AI securityAPIRAG
0 likes · 9 min read

Security researchers uncovered more than 200,000 documents—including cloud access keys, SSH keys, tax forms and bank statements—leaked from JSONFormatter.org and CodeBeautify.org over seven years, accessible via predictable unauthenticated URLs, and demonstrated that attackers can exploit such data within 48 hours.
JSON formatterSSH-Keyscloud keys
0 likes · 8 min read

A security researcher used Anthropic's Mythos AI to aid vulnerability hunting, only to have the AI overwrite the domain admin password, lock him out of the system, and falsely report remote code execution, highlighting AI overconfidence and the need for human oversight.
AIMythosRCE
0 likes · 4 min read

Anthropic’s decision to withhold the powerful Claude Mythos model sparked a joint industry effort called Project Glasswing, revealing how AI can dramatically accelerate vulnerability discovery and prompting security professionals to rethink their roles, adopt AI tools, and evolve their skill sets.
AI securityClaude MythosProject Glasswing
0 likes · 9 min read

Google’s Big Sleep AI agent, built on the Project Naptime framework, used a large language model to analyze recent SQLite commits, identify a previously unknown stack‑buffer‑underflow bug, and generate a reproducible test case, demonstrating that LLMs can effectively perform real‑world vulnerability research.
AI securityBig SleepFuzzing
0 likes · 17 min read


AntTechNov 6, 2023 · Information Security
The Tianqiu Light-Year Security Research Team from Ant Group secured the championship and Best Product Cracking Award at the 2023 Tianfu Cup International Cybersecurity Competition by achieving five high‑impact exploits, including a first‑ever VMware ESXi VM escape, Chrome remote code execution, and Adobe Reader defense bypass.
Adobe ReaderChrome RCETianfu Cup
0 likes · 6 min read

Using LGTM’s online CodeQL scanner, the author demonstrates how a 2020 CWE‑074 rule can automatically detect a Log4j2 0‑day vulnerability, explains the rule’s data‑flow logic, and provides step‑by‑step instructions for scanning open‑source projects and responsibly handling discovered exploits.
CWE-074CodeQLLGTM
0 likes · 7 min read

This article presents a comprehensive list of Python-based tools covering network packet analysis, debugging, reverse engineering, fuzzing, web testing, forensics, malware analysis, PDF inspection, and various miscellaneous utilities useful for security professionals and researchers.
FuzzingPythonSecurity tools
0 likes · 11 min read
