jm + via:adulau + papers   2

'Poisoning Attacks against Support Vector Machines', Battista Biggio, Blaine Nelson, Pavel Laskov
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
papers  svm  machine-learning  poisoning  auto-learning  security  via:adulau 
july 2012 by jm
Comparing genomes to computer operating systems in terms of the topology and evolution of their regulatory control networks — PNAS
'we present a comparison between the transcriptional regulatory network of a well-studied bacterium (E. coli) and the call graph of a canonical OS (Linux) in terms of topology and evolution. ... both networks have a fundamentally hierarchical layout, but there is a key difference: The transcriptional regulatory network possesses a few global regulators at the top and many targets at the bottom; conversely, the call graph has many regulators controlling a small set of generic functions. This top-heavy organization leads to highly overlapping functional modules in the call graph, in contrast to the relatively independent modules in the regulatory network. ... These findings stem from the design principles of the two systems: robustness for biological systems and cost effectiveness (reuse) for software systems.' (via adulau)
via:adulau  papers  toread  genetics  genome  call-graph  linux  kernel  e-coli  operating-systems  transcriptional-regulatory-network  from delicious
may 2010 by jm

Copy this bookmark: