Sciweavers

25 search results - page 2 / 5
» Learning in the Limit with Adversarial Disturbances
Sort
View
CHES
2011
Springer
240views Cryptology» more  CHES 2011»
12 years 4 months ago
Lightweight and Secure PUF Key Storage Using Limits of Machine Learning
A lightweight and secure key storage scheme using silicon Physical Unclonable Functions (PUFs) is described. To derive stable PUF bits from chip manufacturing variations, a lightwe...
Meng-Day (Mandel) Yu, David M'Raïhi, Richard ...
IJCNN
2006
IEEE
13 years 10 months ago
Reinforcement Learning Control for Biped Robot Walking on Uneven Surfaces
— Biped robots based on the concept of (passive) dynamic walking are far simpler than the traditional fullycontrolled walking robots, while achieving a more natural gait and cons...
Shouyi Wang, Jelmer Braaksma, Robert Babuska, Daan...
CDC
2010
IEEE
113views Control Systems» more  CDC 2010»
12 years 11 months ago
Independent vs. joint estimation in multi-agent iterative learning control
This paper studies iterative learning control (ILC) in a multi-agent framework. A group of agents simultaneously and repeatedly perform the same task. The agents improve their perf...
Angela Schöllig, Javier Alonso-Mora, Raffaell...
NSDI
2008
13 years 7 months ago
Exploiting Machine Learning to Subvert Your Spam Filter
Using statistical machine learning for making security decisions introduces new vulnerabilities in large scale systems. This paper shows how an adversary can exploit statistical m...
Blaine Nelson, Marco Barreno, Fuching Jack Chi, An...
ASIACRYPT
2011
Springer
12 years 4 months ago
The Leakage-Resilience Limit of a Computational Problem Is Equal to Its Unpredictability Entropy
A cryptographic assumption is the (unproven) mathematical statement that a certain computational problem (e.g. factoring integers) is computationally hard. The leakage-resilience l...
Divesh Aggarwal, Ueli Maurer