Security
A growing number of studies suggest that machine learning algorithms can leak a considerable amount of information included in the data used to train them through their model parameters and predictions. As a result, malicious ...
Apr 25, 2022 feature
0
247
Security
Researchers at IBM have recently devised a new technique to virtually patch security vulnerabilities before they are found. Their approach, presented at the International Workshop on Information and Operational Technology, ...
Feb 15, 2019 feature
1
86
Security
A team of researchers from R&D company Draper and Boston University developed a new large-scale vulnerability detection system using machine learning algorithms, which could help to discover software vulnerabilities faster ...
Jul 24, 2018 feature
2
206
Computer Sciences
Add one more vulnerability to the list of side-channel attacks that have long dogged Intel CPUs.
Apr 26, 2023 report
0
110
Hi Tech & Innovation
Researchers at the University of California, Irvine have discovered that the safe operation of a negative pressure room—a space in a hospital or biological research laboratory designed to protect outside areas from exposure ...
Nov 17, 2022
2
849
Security
PingSafe AI, a security company that monitors multiple breaches in real time, has uncovered a critical vulnerability in the iPhone automatic call recorder application that exposed thousands of users' recorded calls.
Mar 10, 2021 report
0
48
Consumer & Gadgets
A flaw in a Bluetooth protocol is leaving millions of devices vulnerable to attacks, according to a study released by a Swiss research institute.
May 21, 2020 report
0
334
Energy & Green Tech
(TechXplore)—A trio of researchers with Northwestern University has found vulnerabilities in the North American electrical grid by creating a simulation using real data. In their paper published in the journal Science, ...
Nov 17, 2017 report
0
130
Security
(Phys.org) —Microsoft issued a security advisory on Saturday regarding an issue that impacts the Internet Explorer Web browser. Microsoft said it was aware of limited, targeted attacks seeking to exploit the vulnerability ...
Apr 28, 2014 weblog
2
837
Computer Sciences
A team of researchers with members from MIT, UC Berkely and FAR AI has created a computer program to target vulnerabilities in the KataGo program that allow it to beat the AI-based system. They have published a paper describing ...
Nov 8, 2022 report
0
79
