THREAT OPS › Threat News › AI for Offensive Security: What Works, What Does Not, and How to Adopt It
AI for Offensive Security: What Works, What Does Not, and How to Adopt It
<p class="wp-block-paragraph">Companies frequently ask SpecterOps some version of the same question: <strong>How are you using AI in offensive security, and how can we begin using it too?</strong> They want practical guidance. Which parts of an assessment are improving now? Where does the technology still fail? What should a team learn or build&nbs
MITRE ATT&CK techniques
Indicators of compromise
- https://app.livestorm.co/specterops/how-ai-changes-red-teamingurl
- https://www.fbi.gov/investigate/cyber/alerts/2025/senior-us-officials-impersonated-in-malicious-messaging-campaignurl
- https://arxiv.org/pdf/2512.09882url
- https://www.aisi.gov.uk/blog/our-evaluation-of-openais-gpt-5-5-cyber-capabilitiesurl
- https://arxiv.org/abs/2410.03225url
- https://openai.com/index/hugging-face-incident-and-the-road-ahead/url
- https://www.anthropic.com/research/investigating-incidents-cybersecurity-evalsurl
- https://research.meta.ai/blog/addressing-third-party-testing-misconfiguration-muse-spark-1-1url
- https://www.anthropic.com/threat-intelligence-report-september-2026url
- https://developers.openai.com/blog/skills-agents-sdkurl
- https://docs.langchain.com/oss/python/concepts/productsurl
- https://www.aisi.gov.uk/blog/how-fast-is-autonomous-ai-cyber-capability-advancingurl
Original source: https://specterops.io/blog/2026/09/24/ai-for-offensive-security/