Google AI no longer to use Gender Labels to Tag Photos

Google's Cloud Vision API is a Google Artificial Intelligence (AI) tool that recognizes an image and what's in it and labels it, will no longer use gender labels like "man" and "woman", instead it will label it as 'Person.' Google Cloud Vision API is a tool through which developers can attach labels to photos and identify the content. In an email sent to users on Thursday, Google instructed that they will not use 'woman' or 'man' as physical appearance can not determine gender, the change has been done to avoid bias.

“Given that a person’s gender cannot be inferred by appearance,” reads the email, “we have decided to remove these labels to align with the Artificial Intelligence Principles at Google, specifically Principle #2: Avoid creating or reinforcing unfair bias.” The bias that Google talks about is a result of "flawed training data," a much-discussed topic. A flaw that results in AI algorithm making assumptions- that is anyone who doesn't fit the algorithm of 'man' or 'woman' and will be misgendered. By labeling them as 'person,' Google attempts to avoid this mistake.

Frederike Kaltheuner, a tech policy fellow at Mozilla, said to Business Insider, "Anytime you automatically classify people, whether that's their gender or their sexual orientation, you need to decide on which categories you use in the first place — and this comes with lots of assumptions. "Classifying people as male or female assumes that gender is binary. Anyone who doesn't fit it will automatically be misclassified and misgendered. So this is about more than just bias — a person's gender cannot be inferred by appearance. Any AI system that tried to do that will inevitably misgender people."

Google notes this bias in its API and AI(artificial intelligence) algorithm and seeking to change this flaw: "We will seek to avoid unjust impacts on people, particularly those related to sensitive characteristics such as race, ethnicity, gender, nationality, income, sexual orientation, ability, and political or religious belief." Any more news regarding the Tag feature is yet to be heard from Google.

source https://www.ehackingnews.com/2020/02/google-ai-no-longer-to-use-gender_24.html

Comments

Betting and Gambling Websites under Cyberattack from Chinese Hackers

Since last year's summers, Chinese hackers have been targeting South Asian companies that own online gambling and betting websites. The gambling companies in South Asia have confirmed the hacks, whereas rumors of cyberattacks on betting websites have also emerged from Europe, and the Middle East, however, the rumors are yet to confirm, says the reports of cybersecurity group Trend Micro and Talent-Jump. Cybersecurity experts claim that no money was stolen in these hacks against the gambling websites. However, hackers have stolen source codes and databases. The motive of the attack was not a cybercrime, but rather espionage intended attack to gain intelligence. According to the experts, a group named ' DRBControl ' is responsible for the cyberattack. According to the reports of Trend Micro, the hacking techniques used in this particular cyberattack incident is similar to methods done by Emissary Panda and Winnti. All of these hacking groups are from China that has launc...

Provider Volia reported to the cyber police about the intense cyberattacks on the server

Cable provider Volia appealed to the Cyber Police on the fact of fixing a DDoS attack on the Kharkov servers of the company, which has been ongoing since May 31. "For three days, from May 31 to today, the Volia infrastructure in Kharkov is subjected to cyberattacks. At first, they were carried out only on subscriber subsystems, later they switched to telecommunications infrastructure. As a result, more than 100,000 subscribers experienced problems using the Internet, IPTV, multi-screen platform, and digital TV," said the company. In total, the complete lack of access to Volia's services, according to the provider, lasted 12 minutes on May 31, 45 minutes on June 1. There was also an attack on the website volia.com, but it was managed to neutralize. "DDoS attacks were massive and well-organized. The type of attack is UDP flood and channel capacity overflow with the traffic of more than 200 GB. UDP is a protocol used for online streaming services - streaming, te...

Information security experts have warned Russians about bonus card fraud schemes.

Fraudsters several thousand times tried to illegally take advantage of discount bonuses of Russians in 2019. Some attackers gained access to customers' personal accounts, and then bought the products using bonuses, said Alexey Sizov, head of the anti-fraud department of the Application Security Systems Center at Jet Infosystems. According to him, a fraudster can register a personal account on a card that was issued to another person. The victim will accumulate points without knowing about the existence of his profile, and the attacker will write off bonuses, said Sizov. The expert added that this is mainly done by novice scammers. According to him, loyalty programs are poorly protected, unlike banking operations. He said that they are estimated at 50 billion rubles ($760 milliard) for the 30 largest retailers. Alexey Fedorov, Chairman of the Business Russia Trade Committee, said that in 2019, the number of bonus and discount thefts "increased significantly." ...

Hacking and Cyber Security News

Search This Blog