Large language models (LLMs) have become essential tools for organizations, with open weight models providing additional control and flexibility for

Cisco's platform provides networking knowledge, offering  guides, tutorials, and case studies on networking technologies, cybersecurity, and collaboration tools. Whether you're a networking novice looking to understand the basics of routing and switching or a seasoned IT professional seeking advanced insights into network architecture and security protocols, Cisco has resources tailored to your needs. Dive into Cisco's extensive library of resources to sharpen your networking skills and stay ahead in the rapidly evolving world of IT infrastructure.

Cisco

Cisco researchers evaluated the security posture of OpenAI's gpt-oss and gpt-oss-safeguard models (20b and 120b variants) against adversarial prompt injection and jailbreak attacks. Key findings: multi-turn attacks are the dominant threat, causing attack success rates to jump 5x–8.5x compared to single-turn attacks across all variants. The 120b standard model showed the strongest single-turn resilience, while safeguard variants sometimes introduced exploitable complexity. Model size proved a stronger predictor of baseline resilience than safeguard tuning. Since these are open-weight models, anyone can deploy them in chat settings regardless of OpenAI's intended use case. The analysis recommends a defense-in-depth approach including real-time monitoring, content filtering, rate limiting, and continuous red-teaming rather than relying on model selection alone.

How safe are gpt-oss-safeguard models?