Provably Secure Machine Learning
Neyman Seminar
Jan 29, 2018, 04:00 PM - 05:00 PM | 1011 Evans Hall | Happening As Scheduled
Jacob Steinhardt, Stanford University
Deployed machine learning systems create a new class of computer security vulnerabilities
where, rather than attacking the integrity of the software itself, malicious actors exploit the
statistical nature of the learning algorithms. For instance, attackers can add fake training data,
or strategically manipulate input covariates at test time.
Attempts so far to defend against these...