Sciweavers

21 search results - page 2 / 5
» Machine learning attacks against the Asirra CAPTCHA
Sort
View
SCN
2010
Springer
142views Communications» more  SCN 2010»
13 years 3 months ago
How to Pair with a Human
We introduce a protocol, that we call Human Key Agreement, that allows pairs of humans to establish a key in a (seemingly hopeless) case where no public-key infrastructure is avail...
Stefan Dziembowski
ICC
2007
IEEE
133views Communications» more  ICC 2007»
13 years 11 months ago
Machine Learning for Automatic Defence Against Distributed Denial of Service Attacks
— Distributed Denial of Service attacks pose a serious threat to many businesses which rely on constant availability of their network services. Companies like Google, Yahoo and A...
Stefan Seufert, Darragh O'Brien
CCS
2006
ACM
13 years 9 months ago
Can machine learning be secure?
Machine learning systems offer unparalled flexibility in dealing with evolving input in a variety of applications, such as intrusion detection systems and spam e-mail filtering. H...
Marco Barreno, Blaine Nelson, Russell Sears, Antho...
CCS
2008
ACM
13 years 7 months ago
Open problems in the security of learning
Machine learning has become a valuable tool for detecting and preventing malicious activity. However, as more applications employ machine learning techniques in adversarial decisi...
Marco Barreno, Peter L. Bartlett, Fuching Jack Chi...
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...