7OpenAI Blog·
OpenAI introduces GPT-Red, an automated self-play red teaming system
OpenAI has published details on GPT-Red, an automated red teaming system that uses self-play to iteratively improve AI robustness against adversarial prompts, safety failures, and prompt injection attacks. The system is designed to enable self-improvement loops for alignment and safety testing without requiring constant human red teamers. This represents a notable step toward scalable automated safety evaluation infrastructure.
Related guides (3)
Related events (8)
OpenAI's GPT-Red: an adversarial LLM used to harden models against cyberattacks
OpenAI has developed GPT-Red, an adversarial LLM designed to act as a sparring partner for its production models, stress-testing their defenses against cyberattacks. The system was used in training GPT-5.6, OpenAI's latest flagship model released last week, which the company claims is its most robust release to date. GPT-Red automates red-teaming at scale, representing a shift toward using AI systems to evaluate and improve AI safety properties.
Advancing Red Teaming with People and AI
OpenAI published a blog post describing advances in their red teaming methodology, combining human red teamers with AI-assisted approaches. The post outlines how AI tools are being integrated into the red teaming pipeline to improve coverage and efficiency of safety evaluations. This represents an evolution in OpenAI's pre-deployment safety testing practices.
OpenAI Red Teaming Network
OpenAI is launching an open call for a Red Teaming Network, inviting domain experts to participate in ongoing safety evaluations of its models. The initiative aims to build a structured community of external red teamers who can help identify risks and failure modes across OpenAI's model releases. This represents a formalization of OpenAI's external adversarial testing program beyond one-off pre-release red teaming exercises.
Continuously hardening ChatGPT Atlas against prompt injection
OpenAI is applying automated red teaming trained with reinforcement learning to harden ChatGPT Atlas, its browser agent, against prompt injection attacks. The approach creates a proactive discover-and-patch loop to identify novel exploits before they can be weaponized. This work is framed as part of broader efforts to secure increasingly agentic AI systems against adversarial manipulation of external content.
Red-Teaming Large Language Models
This Hugging Face blog post introduces red-teaming as a safety evaluation methodology for large language models, explaining how adversarial testing can surface harmful outputs, biases, and failure modes before deployment. It covers techniques for systematically probing LLMs to elicit problematic behaviors and discusses the role of red-teaming in responsible AI development. The post serves as an educational overview aimed at practitioners working on LLM safety.
Introducing the Red-Teaming Resistance Leaderboard
Hugging Face and Haize Labs have launched a Red-Teaming Resistance Leaderboard to systematically benchmark how well AI models resist adversarial prompting and jailbreak attempts. The leaderboard provides a standardized evaluation framework for comparing model robustness against red-teaming attacks. This fills a gap in the evaluation ecosystem where safety and adversarial robustness metrics have been less formalized than capability benchmarks.
SafetyKit scales risk agents with OpenAI's most capable models
SafetyKit, a content moderation and compliance platform, has integrated OpenAI's GPT-5 to power its risk-detection agents. The deployment targets content moderation accuracy and compliance enforcement, positioning itself as a replacement for legacy safety systems. This represents a production enterprise use case of GPT-5 in trust and safety workflows.
OpenAI Releases GPT-5.2 System Card Update
OpenAI has published a system card update for GPT-5.2, the latest model family in the GPT-5 series. The safety mitigation approach is described as largely consistent with the prior GPT-5 and GPT-5.1 system cards. Training data sources follow the same pattern as other OpenAI models: publicly available internet data, third-party partnerships, and user/researcher-generated content.