“One of the challenges with anomaly detection, especially when using deep learning techniques, is that it’s sometimes difficult to understand why certain transactions or companies were singled out as suspicious. Strictly speaking, the machine simply yields groupings and anomalies, hence requiring a human specialist to interpret the results. But what if an AI could tell us not only what the anomalies are, but also why they were classified as such? This emerging discipline is called explainable AI (XAI).”
- “80% of web traffic becomes API traffic, they’re coming under threat. Gartner predicts that by 2021, 90% of web apps will have more surface area for attacks in the form of exposed APIs than frontends.
- Salt analyzes a copy of the traffic from web, software-as-a-service, mobile, microservice, and internet of things app APIs. It uses this process to gain an understanding of each API and creates a baseline of normal behavior tailored to customers and their apps. From these baselines, Salt identifies anomalies that might be indicators of an attack”
“Kount, the leader in digital fraud protection and identity trust, today announced independent research firm Mercator Advisory Group has ranked Kount the best eCommerce Fraud Detection Solution in its vendor comparison, published this month. Mercator analysts assessed more than 40 fraud prevention providers and selected five that offer complete solutions for a detailed comparison across five attributes. Kount ranked highest overall with a 4.58 out of 5, as well as first in two categories.”
- “AI is also very useful for identifying user behavior patterns, for the benefit of their security.
- Among the most common risks today in online security, is Poodle, a modality that seeks to obtain access data, by deciphering the information that is revealed during its online submission.”
“Right now, our target customers are financial and fintech startups, as well as other companies deploying the automated process (both software and RPA) in their financial processes,” he added. “The financial systems are our current focus, but the attacks on machine learning are relevant in many other areas: process automation, e-commerce, manipulation of ‘trend detection’ algorithms in social media and other opportunities.”