Attacks on AI: data cleaning becomes a cybersecurity issue
● Artificial intelligence (AI) technologies, including generative AI systems like ChatGPT and predictive AI systems used for self-driving cars and medical diagnostics may be subject to attacks by malicious hackers.
● A recent report by the American National Institute of Standards and Technology has identified a wide range of possible attacks, among them model poisoning, privacy attacks and attempts to repurpose generative AI to produce malevolent content.
● One of the report’s authors, Apostol Vassilev, highlights the need for the standardization and systematic cleaning of training data, as well as constant monitoring to ensure that compromised systems are detected rapidly.
Read the article
● A recent report by the American National Institute of Standards and Technology has identified a wide range of possible attacks, among them model poisoning, privacy attacks and attempts to repurpose generative AI to produce malevolent content.
● One of the report’s authors, Apostol Vassilev, highlights the need for the standardization and systematic cleaning of training data, as well as constant monitoring to ensure that compromised systems are detected rapidly.
FoodProX uses machine learning to detect ultra-processed food
Read the article
IoT and micromobility to benefit from smarter more sustainable batteries
Read the article
Heatwaves: how technology is affected by soaring temperatures
Read the article
Money laundering: a novel approach with new algorithms to combat smurfing
Read the article
