HomeSymrise’s new portfolio uses ai to crack the code of ancient recipes for new taste balancing ingredients

Symrise’s new portfolio uses ai to crack the code of ancient recipes for new taste balancing ingredients

14:52, 14/09/2021
Artificial intelligence (AI) has disrupted countless industries thanks lớn one game-changing property: its ability khổng lồ automate simple tasks that only humans could traditionally vày. Now, that powerful capability is on the verge of disrupting the cybersecurity battlefield. We need to address this AI trend to prevent it from giving criminals the advantage.

Bạn đang xem: Symrise’s new portfolio uses ai to crack the code of ancient recipes for new taste balancing ingredients


Unlượt thích traditional computer algorithms, AI doesn’t follow predefined rules. It analyzes many complex inputs, producing powerful statistical models that can recognize images, interpret human speech, & even "read" text to lớn extract key concepts. This ability khổng lồ carry out small but complex tasks makes it a useful tool for attackers who need khổng lồ vì this often và at scale.

Reconnaissance is one of the first stages in an attack và one area where AI could help attackers hone their efficiency. During this phase, the would-be intruder scours the public domain for information about the target. In early cyberattacks, this mainly involved network scanning. These days, there is so much information available through social truyền thông media sites, company reports & news articles that attackers are drowning in targeted intelligence.

AI promises lớn be the perfect tool for collecting, collating and analyzing this data. In 2017, researchers at Blachồng Hat presented a system for mining data about organizations & executives và using machine learning khổng lồ process it for business tin nhắn compromise (BEC) attacks. The result was an automated tool for creating convincing emails with spoofed header fields.

Reconnaissance AI can also pick up valuable information about how people write. A year before the Blaông chồng Hat presentation, cybersecurity company ZeroFOX wrote a machine learning-based software program that analyzed Twitter posts from targeted individuals along with a broader corpus of general tweets. It used this information lớn automatically create realistic-looking tweets targeting high-value users that could be seeded with a malicious URL.

A new era of fake

Mechanically gathering & processing large amounts of data for use in automated attacks makes it easier for hackers to lớn scale up their operations.

“Attackers need highly repeatable models that allow them khổng lồ carry out the same attacks time and time again on different networks,” explains Charl van der Walternative text, Head of Security Retìm kiếm at Orange Cyberdefense. “Not every attack will be successful, but the more attempts they make, the increased probability of effective penetration of a network. It’s a numbers game.”

*

AI also makes these attacks more convincing. The days of poorly-worded phishing attacks littered with misspellings may be drawing khổng lồ a cchiến bại.

AI is getting better at replicating people, not just in the written word but also in images và videos. Deepfakes use generative sầu adversarial networks (GAN), which are machine learning-based neural networks that compete against each other khổng lồ produce the most convincing outcome. One network tries khổng lồ create an artificial artifact while the other tries lớn spot flaws in it. They create a positive feedback loop, each trying to lớn better the other until a convincing asset emerges. Intelligence services have sầu already used deepfakes in social engineering attacks on LinkedIn to build networks of contacts.

While hobbyists around the world have stunned us with video-based deepfakes that seem lớn show comedian Bill Hader morphing into Tom Cruise, a more immediate danger to lớn companies may come from voice cloning. This giải pháp công nghệ applies similar effects to lớn đoạn Clip, enabling people to lớn mimic others’ voices in real time.

Voice deepfakes create plenty of opportunities for social engineering via phone. Since 2019, organizations have sầu seen multiple cases of attempted voice deepnhái fraud as attackers train neural networks khổng lồ impersonate high-value targets using footage from YouTube and elsewhere.

Xem thêm: Trích Lục Đất Là Gì ? Tại Sao Phải Trích Lục Thửa Đất? Trích Lục Thửa Đất Là Gì

Software-based hackers

Attackers are making advances in other malicious AI use cases, too. In 2016, DARPA held a Cyber Gr& Challenge that pitted teams with AI-powered software algorithms against each other. With impressive sầu results, each attempted to either hack or defkết thúc electronic networks in a game of automated mèo & mouse.

Researchers have been busy creating algorithms that use machine learning lớn demo cybersecurity defenses &, in some cases, bypass them altogether. At the same Blaông xã Hat conference that saw the BEC automation attaông xã, researchers also presented AVPASS, a tool that used AI khổng lồ work out how antivi khuẩn programs detected malware in Android applications và then disguised software khổng lồ circumvent them – with a zero-percent detection rate.

Security firm Bicửa hàng Fox also demonstrated DeepHachồng, a tool that uses machine learning for automated web application penetration testing. Others have sầu created GAN-based password-guessing software. Whereas traditional systems use brute-force techniques to lớn iterate through millions of passwords, PassGAN uses AI khổng lồ extrapolate from previously-leaked passwords, using probability scores to come up with likely variations. The result is a system that could make it easier for attackers lớn access supposedly secure accounts.

Van der Walternative text expects AI attacks to grow in sophistication over time, pervading even more parts of the attachồng chain. “The types of AI-based attacks we expect khổng lồ see include ‘DeepPhishing’ (using deep learning to bypass AI-based phishing detection), fooling deep learning-based image recognition, web application attacks, and bug hunting in libraries,” he warns, adding that these techniques are all at early stages of development.

Other possible criminal uses for AI include detection evasion. Software might watch the environment around it after it has infected a target, modifying its behavior to blkết thúc in with existing traffic. It could also make decisions about how it attempts khổng lồ spread to lớn the rest of the network and even about which data lớn target và exfiltrate.

Do not despair

We must not panic over the malicious possibilities of AI. They exist, but we are not defenseless. We must consider possible mitigations and look at the potential upsides of AI from a cybersecurity perspective sầu. As Europol outlines in its November 2020 report on AI and cybersecurity, we can promote best governance practices around this technology that will help lớn keep things secure. For example, we could encourage those publishing new AI retìm kiếm to lớn include information that would help detect or otherwise mitigate the weaponization of their work. There is already counter research that can help automatically detect deepfakes by spotting anomalies in GAN-generated images & đoạn phim.

We can also use AI ourselves as another layer of defense. Financial services companies already use it for fraud detection, while numerous companies are now using machine learning to lớn detect abnormalities in everything from software to emails & even user behavior.

As with most enabling technologies, AI can be a weapon or a tool. For every attacker who chooses to use it irresponsibly, there are plenty of engineers creating powerful cybersecurity tools that could use AI to lớn turn the tables on attackers.

The Orange Cyberdefense Security Navigator 2021 report has been released. It includes first-hvà information from our 17 global SOCs and CyberSOCs, the Epidemiology Labs & World Watch as well as expert reports & giải pháp công nghệ reviews on topics lượt thích videoconferencing solutions và the cybercrime ecosystem. Download the report lớn find out what the most disrupting events in 20đôi mươi were and how that projects into lớn the future.