Security Blog
The latest news and insights from Google on security and safety on the Internet
Leveraging AI to protect our users and the web
20 de abril de 2018
Posted by Elie Bursztein, Anti-Abuse Research Lead - Ian Goodfellow, Adversarial Machine Learning Research Lead
Recent advances in AI are transforming how we combat fraud and abuse and implement new security protections. These advances are critical to meeting our users’ expectations and keeping increasingly sophisticated attackers at bay, but they come with brand new challenges as well.
This week at RSA, we explored the intersection between AI, anti-abuse, and security in two talks.
Our
first talk
provided a concise overview of how we apply AI to fraud and abuse problems. The talk started by detailing the fundamental reasons why AI is key to building defenses that keep up with user expectations and combat increasingly sophisticated attacks. It then delved into the top 10 anti-abuse specific challenges encountered while applying AI to abuse fighting and how to overcome them. Check out the infographic at the end of the post for a quick overview of the challenges we covered during the talk.
Our
second talk
looked at attacks on ML models themselves and the ongoing effort to develop new defenses.
It covered attackers’ attempts to recover private training data, to introduce examples into the training set of a machine learning model to cause it to learn incorrect behaviors, to modify the input that a machine learning model receives at classification time to cause it to make a mistake, and more.
Our talk also looked at various defense solutions, including differential privacy, which provides a rigorous theoretical framework for preventing attackers from recovering private training data.
Hopefully you were to able to join us at RSA! But if not, here is
re-recording
and
the slides
of our first talk on applying AI to abuse-prevention, along with the
slides
from our second talk about protecting ML models.
Nenhum comentário :
Postar um comentário
Marcadores
#sharethemicincyber
#supplychain #security #opensource
android
android security
android tr
app security
big data
biometrics
blackhat
C++
chrome
chrome enterprise
chrome security
connected devices
CTF
diversity
encryption
federated learning
fuzzing
Gboard
google play
google play protect
hacking
interoperability
iot security
kubernetes
linux kernel
memory safety
Open Source
pha family highlights
pixel
privacy
private compute core
Rowhammer
rust
Security
security rewards program
sigstore
spyware
supply chain
targeted spyware
tensor
Titan M2
VDP
vulnerabilities
workshop
Archive
2024
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2023
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2022
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2021
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2020
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2019
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2018
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2017
dez.
nov.
out.
set.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2016
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2015
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
jan.
2014
dez.
nov.
out.
set.
ago.
jul.
jun.
abr.
mar.
fev.
jan.
2013
dez.
nov.
out.
ago.
jun.
mai.
abr.
mar.
fev.
jan.
2012
dez.
set.
ago.
jun.
mai.
abr.
mar.
fev.
jan.
2011
dez.
nov.
out.
set.
ago.
jul.
jun.
mai.
abr.
mar.
fev.
2010
nov.
out.
set.
ago.
jul.
mai.
abr.
mar.
2009
nov.
out.
ago.
jul.
jun.
mar.
2008
dez.
nov.
out.
ago.
jul.
mai.
fev.
2007
nov.
out.
set.
jul.
jun.
mai.
Feed
Follow @google
Follow
Give us feedback in our
Product Forums
.
Follow
Nenhum comentário :
Postar um comentário