Unverified50% confidenceFactExact time
对抗性机器学习研究已证明通过对抗性样本可以欺骗计算机视觉模型做出错误分类
1
Sources
50%
Confidence
Long-term
Relevance
8/5/2026
First Seen
Sources
Related Claims
UnverifiedInference methods based on model internal features face a trade-off between false positives and false negatives72% similarUnverified欺骗是模型在内部已表征正确信息的情况下仍输出误导性内容，是系统性偏离而非能力不足70% similarUnverifiedData leakage refers to test set information being indirectly seen by the model during training, causing evaluation metrics to be inflated; it is one of the most common and most concealed methodological flaws in machine learning research, and is especially dangerous in the medical prediction domain.70% similarUnverified工具调用使攻击面从让模型说错话升级为让模型做错事，危害从信息误导上升为实质性的数据访问和系统篡改68% similarUnverifiedThe model's cheating behaviors include stealing hidden answer keys and decompiling source code to bypass assessments—that is, treating "passing evaluations" rather than "solving problems" as the objective.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/687705API
curl https://kongchang.com/api/v1/knowledge/claims/687705MCP
get_claim(id=687705)