Agents at Large | Tracing Illicit OpenAI Agent Activity on Hugging FaceTwo Hugging Face accounts reveal that OpenAI's agents staged relay code, internal probes and ChatGPT account registration beyond the published timeline.Read More
AI ResearchTom HegelSep 16, 2026Agents at Large | Tracing Illicit OpenAI Agent Activity on Hugging Face
AI ResearchGabriel Bernadett-ShapiroAug 13, 2026The Model Is the Malware | What Four Agentic Intrusions Tell Defenders
AI ResearchJuan Andrés Guerrero-SaadeJul 22, 2026Sol Searching | Can Frontier Models Tackle Autonomous Long-Horizon Malware Analysis?
AI ResearchGabriel Bernadett-ShapiroJul 2, 2026Context Engineering | Compaction & Agent Memory for Automated Malware Analysis
AI ResearchPhil StokesMar 19, 2026Building an Adversarial Consensus Engine | Multi-Agent LLMs for Automated Malware Analysis
AI ResearchAleksandar MilenkoskiMar 9, 2026From Narrative to Knowledge Graph | LLM-Driven Information Extraction in Cyber Threat Intelligence
AI ResearchGabriel Bernadett-ShapiroJan 29, 2026Silent Brothers | Ollama Hosts Form Anonymous AI Network Beyond Platform Guardrails
AI ResearchGabriel Bernadett-ShapiroJan 20, 2026LLMs in the SOC (Part 1) | Why Benchmarks Fail Security Operations Teams
AI ResearchPhil StokesJan 13, 2026Inside the LLM | Understanding AI & the Mechanics of Modern Attacks
AI ResearchGabriel Bernadett-ShapiroDec 15, 2025LLMs & Ransomware | An Operational Accelerator, Not a Revolution
AI ResearchAlex DelamotteSep 19, 2025Prompts as Code & Embedded Keys | The Hunt for LLM-Enabled Malware
