PromptArmor 测试发现 DeepSeek、Kimi、GLM、Qwen 遭网络攻击的易感度比…
Are models from China are more likely to exfiltrate data?
AI 导读
PromptArmor 将自家传播最广的攻击样本在多个模型上测试，发现 DeepSeek、Kimi、GLM 和 Qwen 模型对网络攻击的易感度比 GPT、Claude 和 Gemini 模型高 88%。测试覆盖钓鱼、数据外泄和运行恶意软件的倾向等多个网络风险维度，作者称差异显著。
正文
Are models from China are more likely to exfiltrate data?
PromptArmor tested all of our most viral attacks on a mix of models, and found that Deepseek, Kimi, GLM, and Qwen models are 88% more susceptible to cyber attacks than GPT Claude and Gemini models. https://t.co/jetPuMFCSB