Learn More
We show in this paper how several proposed Physical Unclonable Functions (PUFs) can be broken by numerical modeling attacks. Given a set of challenge-response pairs (CRPs) of a PUF, our attacks construct a computer algorithm which behaves indistinguishably from the original PUF on almost all CRPs. This algorithm can subsequently impersonate the PUF, and can(More)
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in parameter space, which leads to lower variance gradient estimates than obtained by regular policy gradient methods. We show that for several complex control tasks, including robust(More)
We investigate the foundations of Physical Unclonable Functions from several perspectives. Firstly, we discuss formal and conceptual issues in the various current definitions of PUFs. As we argue, they have the effect that many PUF candidates formally meet no existing definition. Next, we present alternative definitions and a new formalism. It avoids(More)
—We show in this paper how several proposed Strong Physical Unclonable Functions (PUFs) can be broken by numerical modeling attacks. Given a set of challenge-response pairs (CRPs) of a Strong PUF, our attacks construct a computer algorithm which behaves indistinguishably from the original PUF on almost all CRPs. This algorithm can subsequently impersonate(More)
This paper discusses parameter-based exploration methods for reinforcement learning. Parameter-based methods perturb parameters of a general function approximator directly, rather than adding noise to the resulting actions. Parameter-based exploration unifies reinforcement learning and black-box optimization, and has several advantages over action(More)
We present a model-free reinforcement learning method for partially observable Markov decision problems. Our method estimates a likelihood gradient by sampling directly in parameter space, which leads to lower variance gradient estimates than those obtained by policy gradient methods such as REINFORCE. For several complex control tasks, including robust(More)
Many approaches for object detection based on color coding were published in the RoboCup domain. They are tuned to the typical RoboCup scenario of constant lighting using a static subdivision of the color space. However, such algorithms will soon be of limited use, when playing under changing and finally natural lighting. This paper presents an algorithm(More)
— A common practical problem in mobile robotics is the task to calibrate the robot's sensors. Although, the general mapping of the sensor data to robot-centered world coordinates is given by the hardware configuration, the parameters of this mapping vary even between robots with the same configuration. In the RoboCup domain, these parameters can change(More)
So-called Physical Unclonable Functions are an emerging, new cryptographic and security primitive. They can potentially replace secret binary keys in vulnerable hardware systems and have other security advantages. In this paper, we deal with the cryptanalysis of this new primitive by use of machine learning methods. In particular, we investigate to what(More)
Developing superior artificial board-game players is a widely-studied area of Artificial Intelligence. Among the most challenging games is the Asian game of Go, which, despite its deceivingly simple rules, has eluded the development of artificial expert players. In this paper we attempt to tackle this challenge through a combination of two recent(More)