Cybersecurity AI (CAI) Dataset

We present CAI Dataset, a fourteen-month corpus of cybersecurity LLM trajectories collected through the open-source CAI agent framework, built in response to PentestGPT's finding that expert operator trajectories, not base-model capability, are the bottleneck for cybersecurity LLM performance. CA...

Adapting Large Language Models to Emerging Cybersecurity Using Retrieval Augmented Generation

Security applications are increasingly relying on large language models LLMs for cyber threat detection; however, their opaque reasoning often limits trust, particularly in decisions that require domain-specific cybersecurity knowledge. Because security threats evolve rapidly, LLMs must not only...

Talkin’ SMAC: Alert Labeling and Why It Matters

If you’ve ever worked in a Security Operations Center SOC, you know that it’s a special place. Among other things, the SOC is a massive data-labeling machine, and generates some of the most valuable data in the cybersecurity industry. Unfortunately, much of this valuable data is often rendered...

Our Approach to Data Engineering

Our Approach to Data Engineering At Carbon Black, our R&D team is working on the cutting edge of data engineering. We’ve developed our own language and make our data compile down to bytecode to process super-fast. We’re pushing the boundaries of Kubernetes and Kinesis. And we’re having a blast...

Exposed: 157 GB of sensitive data from Tesla, GM, Toyota & others

By Waqas The IT security researchers at cyber resilience firm Upguard discovered a massive trove of highly sensitive data publically available to be accessed by anyone. The data belonged to hundreds of automotive giants including Tesla, Ford, Toyota, GM, Fiat, ThyssenKrupp, and Volkswagen - Thank...

Malware Information Sharing Platform Cross-Site Scripting Vulnerability

MISP is an open source software solution for collecting, storing, distributing and sharing cybersecurity metrics and threats cybersecurity incident analysis and malware analysis. MISP suffers from a cross-site scripting vulnerability. An attacker can exploit this vulnerability to inject arbitrary...