1
GPT-Red: Unlocking Self-Improvement for Robustness
OpenAI用自我对弈实现自动化红队测试，大幅提升AI安全与提示注入防御能力。
Explore GPT-Red, OpenAI’s automated red teaming system that uses self-play to improve AI safety, alignment, and prompt injection robustness.
2
打造 AI 网安“红队”：OpenAI 介绍内部漏洞检测模型 GPT-Red
OpenAI自曝内部“红队”模型GPT-Red，将提示注入攻击成功率从95%压至0.05%，AI安全实战效果惊人。
IT之家 7 月 16 日消息，OpenAI 当地时间 15 日介绍了其内部使用的网络安全“红队”模型 GPT-Red。 该模型可自动化地进行各种网络攻击模拟 ，帮助 OpenAI 提升对外模型产品的鲁棒性。 OpenAI 表示，其过去半年 自 GPT-5.3 后的每个生产模型均将“红队”模型用于训…
3
Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming
让AI Agent自动互相攻击，发现生产环境漏洞，这篇论文提出了全新的自动化红队测试框架。
arXiv:2607.11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands,…
4
RedCoder: Automated Multi-Turn Red Teaming for Code LLMs
自动化多轮红队测试框架，针对代码大模型的安全漏洞发起精准攻击。
arXiv:2507.22063v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) for code generation (i.e., Code LLMs) have demonstrated impress…
5
Giskard: LLM esting platform for preventing hallucinations and security issues
从多年实战经验出发，深入剖析2026年AI红队工具评估要点，助你防范LLM幻觉与安全漏洞。
Article URL: https://www.giskard.ai/knowledge/best-ai-agent-red-teaming-tools-in-2026-understanding-features-functions-and-solutions Comments URL: htt…
6
RIFT-Bench: Dynamic Red-teaming For Agentic AI Systems
动态评估智能体AI系统安全性的创新基准RIFT-Bench，通过自动化攻击测试揭示大模型潜在风险。
arXiv:2606.23927v1 Announce Type: new Abstract: Agentic AI systems powered by large language models (LLMs) are rapidly evolving into autonomous decisi…
7
AICU – LLM Red Team Vulnerability Scanner
专为LLM设计的红队漏洞扫描工具，帮你发现大模型安全隐患。
Article URL: https://github.com/Jake-Schoellkopf/aicu Comments URL: https://news.ycombinator.com/item?id=48589149 Points: 1 # Comments: 0
8
A Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models
最新Anthropic模型红队安全测试结果，揭露Fable 5与Opus 4.8的脆弱性。
arXiv:2606.18193v1 Announce Type: cross Abstract: We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Ant…
9
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections
论文提出PI-Hunter，自动发现并精准定位大模型提示注入漏洞，为AI安全红队测试提供新方案。
arXiv:2606.12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external t…
10
Learning to Inject: Automated Prompt Injection via Reinforcement Learning
利用强化学习自动化实现提示注入攻击，性能超越人工红队测试
arXiv:2602.05746v2 Announce Type: replace-cross Abstract: Prompt injection is a critical vulnerability in LLM agents, yet the strongest methods still …
11
Anthropic’s Claude Fable 5 is a version of Mythos the public can access today
Anthropic发布Claude Fable 5：超千小时安全测试未发现通用越狱，公开版Mythos模型上线。
Anthropic is releasing Claude Fable 5, its first Mythos-class model available to the public. The model comes with guardrails that block responses in h…
12
Anthropic’s Claude Fable 5 is a version of Mythos the public can access today
Anthropic发布最强模型Claude Fable 5，超千小时测试未发现通用越狱，安全性与性能齐头并进。
Anthropic is releasing Claude Fable 5, its first Mythos-class model available to the public. The model comes with guardrails that block responses in h…
13
Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (and Fail) Red Team Attacks
用流程挖掘揭示大模型红队攻击的成败细节，超越传统二分类评估
arXiv:2606.07833v1 Announce Type: cross Abstract: Standard AI red teaming evaluations reduce adversarial campaigns to a single binary outcome, attack …
14
OTora: A Unified Red Teaming Framework for Reasoning-Level Denial-of-Service in LLM Agents
首个面向LLM Agent推理层拒绝服务攻击的统一红队框架，揭示认知安全盲区与对抗策略。
arXiv:2605.08876v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly deployed as autonomous agents that execute tool-augm…
15
TamperBench: Systematically Stress-Testing LLM Safety Under Fine-Tuning and Tampering
系统性压力测试大模型在微调与篡改下的安全性，为LLM红队评估提供新基准。
arXiv:2602.06911v2 Announce Type: replace-cross Abstract: As increasingly capable open-weight large language models (LLMs) are deployed, improving the…
16
A Multi-Domain Red Teaming Framework for Safety, Robustness, and Fairness Evaluation of Medical Large Language Models
首个针对医疗大语言模型的多领域红队框架，系统评估安全、鲁棒与公平性。
arXiv:2606.00027v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed across healthcare, yet existing benchmarks fa…
17
RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates
多智能体辩论机制让AI自相检验安全漏洞，红队自动生成对抗性攻击，大幅提升大模型回复安全性。
arXiv:2506.11083v3 Announce Type: replace Abstract: We introduce RedDebate, a novel multi-agent debate framework that provides the foundation for Larg…
18
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
动态红队测试与集成感知防御：首个覆盖Gmail、Salesforce等主流SaaS集成的LLM Agent安全基准，揭示间接提示注入的真实威胁。
arXiv:2606.02240v1 Announce Type: cross Abstract: Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from i…
19
SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
自动化红队测试框架，专攻LLM搜索代理的安全漏洞，已被ICML 2026接收。
arXiv:2509.23694v5 Announce Type: replace Abstract: Search agents connect LLMs to the Internet, enabling them to access broader and more up-to-date in…
20
Stable-GFlowNet: Toward Diverse and Robust LLM Red-Teaming via Contrastive Trajectory Balance
提出Stable-GFlowNet，用对比轨迹平衡生成多样对抗样本，提升LLM红队测试的鲁棒性
arXiv:2605.00553v2 Announce Type: replace Abstract: Large Language Model (LLM) Red-Teaming, which proactively identifies vulnerabilities of LLMs, is a…