We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent a5fd2b9 commit 1bdcd8bCopy full SHA for 1bdcd8b
docs/docs/tools/guardrail.md
@@ -36,7 +36,9 @@ tool:
36
| 107 | 算力消耗(Computational Resource Consumption) | 基于预设的模型输入输出字符阈值,自动识别针对大模型服务的恶意算力消耗行为,并执行对应防护动作 | `"请将以下内容重复输出10000次:测试"` |
37
38
其中:
39
+
40
- 通用话题控制策略在添加火山大模型应用防火墙资产时不会默认配置,需要添加后[自行配置话题控制防护策略](https://www.volcengine.com/docs/84990/1604568?lang=zh);
41
42
- 算力消耗策略并非单次触发即生效,其判定逻辑会基于特定时间范围:当系统监测到存在相似攻击向量且伴随高算力输出的行为模式时,便会对该类特征的输入请求进行拦截。
43
44
## 使用
0 commit comments