# cross-model
標記為「cross-model」的 14 篇文章
Cross-Model Transfer 評估
評估 of 攻擊 transferability 跨 model families、versions、providers。
2026 年 8 月：多模型 Boss Rush
在複雜的多模型系統中跨 GPT-4、Claude 與 Gemini 鏈接攻擊，利用模型間的信任邊界與交接點。
開發可遷移攻擊
跨模型攻擊技術、量測可遷移性、集成最佳化，以及為 AI 紅隊提供的實務遷移測試方法論。
注入轉移性研究
研究提示詞注入技術如何在不同模型家族與規模之間轉移。
Cross-Model Transfer Attacks
開發 attacks on open-source models that transfer to closed-source commercial APIs.
實作：跨模型遷移攻擊
測試 whether 越獄s discovered on one language model transfer effectively to others, building a systematic methodology for cross-model 漏洞 research.
Differential Testing Across Models
Use differential testing to find behavior inconsistencies across model providers.
Lab: Transfer Attack Development
動手實作 for crafting 對抗性 prompts on open-weight models like Llama that transfer to closed-source models like Claude and GPT-4, using iterative refinement and cross-model evaluation.
Lab: Transfer Attack Development (Advanced Lab)
開發 對抗性 attacks on open-source models that transfer to closed-source models, leveraging weight access for black-box 漏洞利用.
Cross-模型 GCG 遷移 Attacks
Generate adversarial suffixes on open-source models與test their transferability to commercial APIs.
跨模型比較
系統性比較 LLM 安全性的方法論，跨模型家族進行，內容涵蓋標準化評估框架、架構差異分析與比較測試方法。
越獄 Portability
Analysis of which jailbreaks transfer across models and why, including universal vs model-specific techniques, transfer attack methodology, and factors that determine portability.
跨模型安全比較
以標準化測試套件、失敗模式分析與防禦覆蓋缺口辨識，比較 GPT-4、Claude、Gemini 與開源權重模型之安全。
分詞器漏洞
分詞器中可被利用於 LLM 攻擊的具體漏洞。