AI-Infra-Guard v4.6.1

📖 Documentation | 🌐 🇨🇳 中文 · 🇯🇵 日本語 · 🇪🇸 Español · 🇩🇪 Deutsch · 🇫🇷 Français · 🇰🇷 한국어 · 🇧🇷 Português · 🇷🇺 Русский 🚀 AI Red Teaming Platform by Tencent Zhuque Lab A.I.G AI-Infra-Guard integrates capabilities such as ClawScanOpenClaw Security Scan, Agent Scan，AI infra vulnerability scan...

Fair ASR: Re-Evaluating Black-Box Jailbreaks under Shared Target-Call Budgets

Reliable jailbreak evaluation is essential for assessing LLM safety, but most existing studies rely solely on attack success rate ASR without accounting for its dependence on attack budgets, resulting in unfair comparisons across methods. Existing compute-aware evaluations reduce heterogeneous...

AI-Infra-Guard v4.5.2

📖 Documentation | 🌐 🇨🇳 中文 · 🇯🇵 日本語 · 🇪🇸 Español · 🇩🇪 Deutsch · 🇫🇷 Français · 🇰🇷 한국어 · 🇧🇷 Português · 🇷🇺 Русский 🚀 AI Red Teaming Platform by Tencent Zhuque Lab A.I.G AI-Infra-Guard integrates capabilities such as ClawScanOpenClaw Security Scan, Agent Scan，AI infra vulnerability scan, MCP Server &...

AI-Infra-Guard v4.5.1

📖 Documentation | 🌐 🇨🇳 中文 · 🇯🇵 日本語 · 🇪🇸 Español · 🇩🇪 Deutsch · 🇫🇷 Français · 🇰🇷 한국어 · 🇧🇷 Português · 🇷🇺 Русский 🚀 AI Red Teaming Platform by Tencent Zhuque Lab A.I.G AI-Infra-Guard integrates capabilities such as ClawScanOpenClaw Security Scan, Agent Scan，AI infra vulnerability scan, MCP Server &...

AI-Infra-Guard v4.5.0

📖 Documentation | 🌐 🇨🇳 中文 · 🇯🇵 日本語 · 🇪🇸 Español · 🇩🇪 Deutsch · 🇫🇷 Français · 🇰🇷 한국어 · 🇧🇷 Português · 🇷🇺 Русский 🚀 AI Red Teaming Platform by Tencent Zhuque Lab A.I.G AI-Infra-Guard integrates capabilities such as ClawScanOpenClaw Security Scan, Agent Scan，AI infra vulnerability scan, MCP Server &...

PixJail: Self-Evolving Paper-To-Pipeline Reproduction for Text-To-Image Jailbreak Evaluation

As Text-to-Image T2I jailbreak techniques evolve rapidly, existing benchmarks and reproduction workflows often struggle to keep pace. More importantly, T2I jailbreak evaluation is not a single prompt-level test, but a pipeline-level problem shaped by multiple stages, including prompt...

Quant Fever, Reasoning Blackholes, Schrodinger'S Compliance, and More: Probing GPT-OSS-20B

OpenAI's GPT-OSS family provides open-weight language models with explicit chain-of-thought CoT reasoning and a Harmony prompt format. We summarize an extensive security evaluation of GPT-OSS-20B that probes the model's behavior under different adversarial conditions. Using the Jailbreak Oracle J...

Beyond Uniform Criteria: Scenario-Adaptive Multi-Dimensional Jailbreak Evaluation

Precise jailbreak evaluation is vital for LLM red teaming and jailbreak research. Current approaches employ binary classification e.g., string matching, toxic text classifiers, LLM-driven methods, yielding only "yes/no" labels without quantifying harm intensity. Existing multi-dimensional...