Anthropic reports 90-99% drop in distillation attacks
Briefing by News4U · First published
Anthropic said Monday its new safeguards have reduced data stolen through distillation attacks on Claude by 90-99%, bringing extracted reasoning tokens down to between one-tenth and one-hundredth of previous levels. [1]
Sources
- Anthropic称新防护措施大幅减少了“蒸馏攻击”的数据窃取量
Sina Finance · · Full text
- Anthropic 测试事故：Claude 模型向警方提交虚假凶杀线索，还提交 20 份签证申请
ITHome · · Excerpt