PPhying中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

Unleashing Claude 3.5 Sonnet As A Hacker

josephthacker.com | blog | #bug-bounty | #offensive-security | #llm | #joseph-thacker | #claude-3-5-sonnet | #ai-hacking
📄 Raw .md⬇️ Download .md🔗 Original ↗

Summary

Joseph Thacker explores using the newly released Claude 3.5 Sonnet model for offensive security and bug bounty hacking tasks.
Published
Collected

Related coverage

blog · hackenproof.com
How We Built an Autonomous AI Security Triager: From LLM to 20,000+ Real Reports
AI made bug hunters sharper, and report volume doubled. How HackenProof built an autonomous AI triager that now handles 70% of submissions.
blog · specterops.io
AI for Offensive Security: What Works, What Does Not, and How to Adopt It
SpecterOps maps where AI helps offensive security (recon, tooling, vuln discovery) and where it still fails, stressing that results hinge on the harness: context, tools, state, independent validation, and human judgment.
blog · projectzero.google
Project Naptime: Evaluating Offensive Security Capabilities of Large Language Models
Project Naptime evaluates the offensive security capabilities of large language models, presenting a methodology, tooling setup, and early successes finding real vulnerabilities.
vulnerability · projectdiscovery.io
Beyond the Model: Neo Hunts, Exploits, and Proves 22 Zero-Days.
LLMs find vulnerabilities fast but flood teams with unverified reports. Neo confirmed 22 CVEs across 13 open source projects at ~10-20% false positives, with working exploits and runtime evidence.
blog · josephthacker.com
Operation Floodlight
Joseph Thacker reflects on the downstream impacts of AI systems gaining strong cybersecurity capabilities, in an essay titled Operation Floodlight.
blog · josephthacker.com
Simplify Interviews with guided-capture
The author released guided-capture, a Python package that uses AI to automate structured interviews and gather context for AI applications.
Back