11-19 更新 实时
首页/ 科技公司/ 正文

开源与闭源 AI 模型的网络攻击能力差距持续缩小

科技公司 来源:The Decoder 2026-11-07 23:35 0 阅读 机器翻译
开源与闭源 AI 模型的网络攻击能力差距持续缩小

Nano Banana Pro,提示词由 THE DECODER 提供

Vals AI 发现,AI 智能体能够自行入侵逼真的企业网络

Vals CyberOffense 基准测试通过模拟逼真的企业网络来对此进行检验。每个智能体都在一台隔离的攻击机器上单独运行,起点只有一个公开的网址,且没有任何人类协助。

AI 智能体从一台隔离的 Kali Linux 机器上运行,独立向模拟的企业网络发送命令,并从 Web 应用一路穿透 Windows 服务器,最终取得管理员权限。每一项操作都在外部记录并自动评分。| 图片:Vals AI

GPT-6 Sol 属于 OpenAI 受限的 Daybreak 网络项目,取得了最佳成绩,完成 80.8% 的攻击目标。可自由获取的开放权重模型 Deepseek V4.1 Flash 1017 紧随其后,达到 72.8%,且每次运行成本仅约 3 美元,而非大约 22 美元。Vals 研究人员表示,一旦模型权重公开,任何提供商都无法控制或限制其使用方式。

AI 智能体使用的 Token 越多,达成的攻击目标就越多。GPT-6 Sol Daybreak 以约 80% 领先,Deepseek V4.1 Flash 以约 73% 紧随其后。大多数模型在超过 1 亿 Token 之前都不会取得实质性进展。| 图片:Vals AI

在难度更高的 Lighthouse 测试中,Daybreak 夺取了第一家公司管理员的控制权,窃取密码,并利用这些密码入侵第二家公司。它在不到三小时内完成了 31 个目标中的 27 个。Deepseek 以十分之一的成本完成了 21 个目标,而且限制它的并不只是安全防护机制。

更长的运行时间同样被证明至关重要。Deepseek 在前 2500 万 Token 中得分为零,其大部分进展是在超过 1 亿 Token 之后才取得的。因此,短时测试低估了开放模型的真实潜力。

在较简单的 Nova 测试中,GPT-6 Sol Daybreak 以约 80% 的攻击目标达成率领先;而在难度更高的 Lighthouse 场景中,Deepseek V4.1 Flash 反超所有对手。大多数中国开放模型在超过 1 亿 Token 之前都不会取得实质性进展。因此,短时基准测试低估了它们的潜力。| 图片:Vals A

15.7(3 次平均值,范围 12–19)

Deepseek V4.1 Flash 1017

16.3(3 次平均值,范围 15–18)

Vals 指出,同样的发现也为防御方创造了机会,因为那些能利用漏洞的模型,恰恰可以帮助企业抢先发现并修复漏洞。据 Vals 称,未来几个月针对真实网络的攻击可能会增加。

早期研究证实:开放模型正在快速缩小差距

这些结果与英国 AI 安全研究所(AISI)7 月发布的一项最新分析相吻合。开放前沿模型与闭源前沿模型在网络能力上的差距已缩小到 4 至 7 个月。而在 2025 年的大部分时间里,这一差距仍为 6 至 10 个月。

开放模型的成本也低得多。据 AISI 称,使用 Deepseek V4-Pro 进行一次网络靶场演练仅需 1.19 美元,而 Anthropic 的 Opus 4.5 则需 85 美元。事实证明,这些开放模型上的安全措施基本无效。

Anthropic 最近的一项研究还显示,可免费获取的模型 GLM-5-3 构建漏洞利用程序的能力几乎与内部顶级模型 Mythos 相当。

没有炒作的 AI 新闻——由人类精选

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(The gap between open and closed AI models in cyber capabilities keeps shrinking)

Nano Banana Pro prompted by THE DECODER

AI agents can break into realistic corporate networks on their own, Vals AI finds

The Vals CyberOffense benchmark simulates realistic corporate networks to test this. Each agent operates solo on an isolated attack machine, starting with nothing but a public web address and zero human help.

The AI agent operates from an isolated Kali Linux machine, independently sends commands to the simulated corporate network, and works its way from the web application through Windows servers to admin privileges. Every action is logged externally and scored automatically. | Image: Vals AI

GPT-6 Sol, part of OpenAI's restricted Daybreak cyber program, posted the best result at 80.8 percent of objectives. Deepseek V4.1 Flash 1017, a freely available open-weight model, isn't far behind at 72.8 percent and costs only about $3 per run instead of roughly $22. Once a model's weights are public, no provider can control or restrict how it's used, Vals researchers say.

The more tokens an AI agent uses, the more attack objectives it reaches. GPT-6 Sol Daybreak leads with about 80 percent, while Deepseek V4.1 Flash follows at roughly 73 percent. Most models don't make meaningful progress until they pass 100 million tokens. | Image: Vals AI

In the harder Lighthouse test, Daybreak took over admin control of the first company, stole passwords, and used them to break into the second company. It completed 27 of 31 objectives in under three hours. Deepseek managed 21 objectives at a tenth of the cost and wasn't limited solely by safety guardrails.

Longer runtimes turned out to be critical as well. Deepseek scored zero results in its first 25 million tokens and made most of its progress only after 100 million tokens. Short tests therefore underestimate the real potential of open models.

In the simpler Nova test, GPT-6 Sol Daybreak leads with about 80 percent of attack objectives, while in the harder Lighthouse scenario, Deepseek V4.1 Flash overtakes the field. Most open Chinese models don't make meaningful progress until they pass 100 million tokens. Short benchmarks therefore underestimate their potential. | Image: Vals A

15.7 (average of 3, range 12–19)

Deepseek V4.1 Flash 1017

16.3 (average of 3, range 15–18)

Vals points out that the same findings create an opportunity for defenders, because the very models that exploit vulnerabilities can help companies find and fix them first. Attacks on real networks are likely to increase in the coming months, according to Vals.

Open models close the gap fast, earlier studies confirm

The results align with a recent analysis by the UK's AI Security Institute (AISI) from July. The gap between open and closed frontier models in cyber capabilities has shrunk to four to seven months. For most of 2025, that gap still stood at six to ten months.

Open models are also much cheaper. A cyber-range run with Deepseek V4-Pro costs just $1.19 according to AISI, compared with $85 for Anthropic's Opus 4.5. The safety measures on the open models proved largely ineffective.

A recent study by Anthropic also showed that the freely available model GLM-5-3 can build exploits at nearly the same level as the internal top model Mythos.

AI News Without the Hype – Curated by Humans

原文为英文,正文由自动抓取并保留原文。

本文由采集器自动同步

原文发布于 The Decoder(The gap between open and closed AI models in cyber capabilities keeps shrinking),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗