实体
FGSM
FGSM
PulseAugur coverage of FGSM — every cluster mentioning FGSM across labs, papers, and developer communities, ranked by signal.
总计 · 30天
3
90 天内 3
发布 · 30天
0
90 天内 0
论文 · 30天
3
90 天内 3
层级分布 · 90 天
情绪 · 30 天
3 天有情绪数据
最近 · 第 1/1 页 · 共 3 条
-
安卓恶意软件检测易受概念漂移影响
研究人员对安卓恶意软件检测系统十年的对抗性鲁棒性进行了纵向研究。他们的发现表明，随着时间的推移数据分布发生变化的“概念漂移”会显著降低这些系统的对抗性鲁棒性。尽管使用累积历史数据重新训练模型可以缓解部分损失，但并不能完全消除问题，这凸显了对“漂移感知”评估框架的需求。
-
Simpler ML models show surprising robustness to adversarial attacks
Researchers explored how architectural choices in machine learning models can enhance robustness against gradient-based adversarial attacks. Their extensive experiments revealed that simpler network designs, fewer featu…
-
New attack method predicts gradients, boosting adversarial generation speed
Researchers have developed a new method for generating adversarial examples in machine learning models by predicting gradients from forward-pass hidden states. This technique bypasses the computationally expensive backw…