'The radium girls’ case was one of the first in which an employer was made responsible for the health of the company’s employees. It led to life-saving regulations and, ultimately, to the establishment of the Occupational Safety and Health Administration, which now operates nationally in the United States to protect workers. Before OSHA was set up, 14,000 people died on the job every year; today, it is just over 4,500. The women also left a legacy to science that has been termed “invaluable.”'

The perils of auto-training SVMs on unvetted input.

We investigate a family of poisoning attacks against Support Vector Machines (SVM). Such attacks inject specially crafted training data that increases the SVM's test error. Central to the motivation for these attacks is the fact that most learning algorithms assume that their training data comes from a natural or well-behaved distribution. However, this assumption does not generally hold in security-sensitive settings. As we demonstrate, an intelligent adversary can, to some extent, predict the change of the SVM's decision function due to malicious input and use this ability to construct malicious data. The proposed attack uses a gradient ascent strategy in which the gradient is computed based on properties of the SVM's optimal solution. This method can be kernelized and enables the attack to be constructed in the input space even for non-linear kernels. We experimentally demonstrate that our gradient ascent procedure reliably identifies good local maxima of the non-convex validation error surface, which significantly increases the classifier's test error.

Via Alexandre Dulaunoy