llm 39
- How we fine-tuned a faster model for Patterns on Baseten
- Breaking the Semantic Cache: A LiteLLM Case Study (CVE-2026-89032)
- Abliterated Models in Appsec Pentesting
- The LLM Glue Trap
- From Phishing to LLMjacking: Threat Actors Targeting Cloud Billing Accounts for LLM Usage
- Jev as a judge: How counterfeit policy steers Jev
- Dearbhadh Retrospective
- Beyond valid credentials: How exposed AWS keys are tested for Amazon Bedrock access
- The Temporary Democratization of Software Reverse Engineering
- OpenAI GPT-6 Sol: An evaluation
- Bypassing EDR with Local AI
- LLMHaxor Update
- Monitor prompt caching to optimize your token usage
- Detect vulnerabilities in LLM applications with Datadog’s AI-native SAST
- Web App Pentesting in the AI Era
- Shiny, Sharp Objects
- Phantom Squatting: AI-Hallucinated Domains as a Software Supply Chain Vector
- Large Workflows with Local LLMs
- A new era for software testing
- From prompt to pwned: chaining LLM and web bugs to Admin
- How Neo's Agent Architecture Evolved: From One Agent → Plan, Execute & Verify
- ChatGPhish: The Page Is the Payload
- Let’s talk about encrypted reasoning
- Adversarial Oracles: LLM-Guided EDR Signature Reduction
- Negative-Days with Vulnerability Spoiler Alert: Three Months Later
- How to Secure Your Enterprise LLM Deployment
- Coverage-Driven Sustained Testing (CDST): A Graph-Oriented Model for Open-Ended Agentic Workflows
- Nuclei Templates - April 2026
- Personal Software and BaremetalVMM
- [Deprecated] Break LLM Workflows with Claude's Refusal Magic String
- The Defensive Stack is Exposed: LLMs, Reverse Engineering, and the End of Opaque Defense
- AI cybersecurity is not proof of work
- Benchmarking Self-Hosted LLMs for Offensive Security
- Mythos and its impact on security
- Introducing our open source AI-native SAST
- Bypassing LLM Supervisor Agents Through Indirect Prompt Injection
- How We Cut LLM Costs by 59% With Prompt Caching
- Introducing the Offsec ML Playbook v0.1
- What is LLM Penetration Testing? A Complete Guide