New superbug-killing antibiotic discovered using AI

Scientists have used artificial intelligence (AI) to discover a new antibiotic that can kill a deadly species of superbug.

The AI helped narrow down thousands of potential chemicals to a handful that could be tested in the laboratory.

The result was a potent, experimental antibiotic called abaucin, which will need further tests before being used.

The researchers in Canada and the US say AI has the power to massively accelerate the discovery of new drugs.

It is the latest example of how the tools of artificial intelligence can be a revolutionary force in science and medicine.

[…]

To find a new antibiotic, the researchers first had to train the AI. They took thousands of drugs where the precise chemical structure was known, and manually tested them on Acinetobacter baumannii to see which could slow it down or kill it.

This information was fed into the AI so it could learn the chemical features of drugs that could attack the problematic bacterium.

The AI was then unleashed on a list of 6,680 compounds whose effectiveness was unknown. The results – published in Nature Chemical Biology – showed it took the AI an hour and a half to produce a shortlist.

The researchers tested 240 in the laboratory, and found nine potential antibiotics. One of them was the incredibly potent antibiotic abaucin.

Laboratory experiments showed it could treat infected wounds in mice and was able to kill A. baumannii samples from patients.

However, Dr Stokes told me: “This is when the work starts.”

The next step is to perfect the drug in the laboratory and then perform clinical trials. He expects the first AI antibiotics could take until 2030 until they are available to be prescribed.

Curiously, this experimental antibiotic had no effect on other species of bacteria, and works only on A. baumannii.

Many antibiotics kill bacteria indiscriminately. The researchers believe the precision of abaucin will make it harder for drug-resistance to emerge, and could lead to fewer side-effects.

[…]

Source: New superbug-killing antibiotic discovered using AI – BBC News

Google bans Downloader app after TV firms complain it can load a pirate website – Firefox, Opera, IE, Chrome, Safari: look out!

The Google Play Store suspended an app that combines a web browser with a file manager after a Digital Millennium Copyright Act (DMCA) complaint pointed out that the app is capable of loading a piracy website—even though that same pirate website can be loaded on any standard browser, including Google Chrome.

The free app, which is designed for Android TV devices and is called Downloader, had been installed from Google Play over 5 million times before its suspension on Friday, an Internet Archive capture shows. The suspension notice that Google sent to Downloader app developer Elias Saba cites a complaint from several Israeli TV companies that said the app “allows users to view the infamous copyright infringing website known as SDAROT.”

Saba provided us with a copy of the suspension notice.

“You can see in the DMCA description portion that the only reason given is the app being able to load a website,” Saba told Ars. “My app is a utility app that combines a basic file manager and a basic web browser. There is no way to view content in the app other than to use the web browser to navigate to a website. The app also doesn’t present or direct users to any website, other than my blog at www.aftvnews.com, which loads as the default homepage in the web browser.”

Saba also detailed his frustrations with the takedown in a blog post and a series of tweets. “Any rational person would agree that you can’t possibly blame a web browser for the pirated content that exists on the Internet, but that is exactly what has happened to my app,” he wrote on his blog.

Downloader is still available on the Amazon app store for devices such as Fire TVs, or from the Downloader app’s website as an APK file.

It’s a “standard web browser,” developer says

Before being pulled from Google Play, the app’s description said that Downloader “allows Android TV owners to easily download files from the Internet onto their device. You can enter a URL which directly points to a file, or you can sideload the web browser plugin to download files from websites.”

“If loading a website with infringing content in a standard web browser is enough to violate DMCA, then every browser in the Google Play Store including @googlechrome should also be removed. It’s a ridiculous claim and an abuse of the DMCA,” Saba wrote on Twitter.

[…]

Source: Google bans Downloader app after TV firms complain it can load a pirate website | Ars Technica

Brute-force attack bypasses Android biometric fingerprint defense

Chinese researchers say they successfully bypassed fingerprint authentication safeguards on smartphones by staging a brute force attack.

Researchers at Zhejiang University and Tencent Labs capitalized on vulnerabilities of modern smartphone fingerprint scanners to stage their break-in operation, which they named BrutePrint. Their findings are published on the arXiv preprint server.

A flaw in the Match-After-Lock feature, which is supposed to bar authentication activity once a device is in lockout mode, was overridden to allow a researcher to continue submitting an unlimited number of fingerprint samples.

Inadequate protection of biometric data stored on the Serial Peripheral Interface of fingerprint sensors enables attackers to steal fingerprint images. Samples also can be easily obtained from academic datasets or from biometric data leaks.

[…]

All Android devices and one HarmonyOS (Huawei) device tested by researchers had at least one flaw allowing for break-ins. Because of tougher defense mechanisms in IOS devices, specifically Apple iPhone SE and iPhone 7, those devices were able to withstand brute-force entry attempts. Researchers noted that iPhone devices were susceptible to CAMF vulnerabilities, but not to the extent that successful entry could be achieved.

To launch a successful break-in, an attacker requires physical access to a targeted phone for several hours, a easily obtainable for $15, and access to fingerprint images.

Fingerprint databases are available online through academic resources, but hackers more likely will access massive volumes of images obtained through data breaches.

[…]

More information: Yu Chen et al, BrutePrint: Expose Smartphone Fingerprint Authentication to Brute-force Attack, arXiv (2023). DOI: 10.48550/arxiv.2305.10791

Source: Brute-force test attack bypasses Android biometric defense

A Paralyzed Man Can Walk Naturally Again With ML Brain and Spine Implants

Gert-Jan Oskam was living in China in 2011 when he was in a motorcycle accident that left him paralyzed from the hips down. Now, with a combination of devices, scientists have given him control over his lower body again. “For 12 years I’ve been trying to get back my feet,” Mr. Oskam said in a press briefing on Tuesday. “Now I have learned how to walk normal, natural.” In a study published on Wednesday in the journal Nature, researchers in Switzerland described implants that provided a “digital bridge” between Mr. Oskam’s brain and his spinal cord, bypassing injured sections. The discovery allowed Mr. Oskam, 40, to stand, walk and ascend a steep ramp with only the assistance of a walker. More than a year after the implant was inserted, he has retained these abilities and has actually showed signs of neurological recovery, walking with crutches even when the implant was switched off. “We’ve captured the thoughts of Gert-Jan, and translated these thoughts into a stimulation of the spinal cord to re-establish voluntary movement,” Gregoire Courtine, a spinal cord specialist at the Swiss Federal Institute of Technology, Lausanne, who helped lead the research, said at the press briefing.

In the new study, the brain-spine interface, as the researchers called it, took advantage of an artificial intelligence thought decoder to read Mr. Oskam’s intentions — detectable as electrical signals in his brain — and match them to muscle movements. The etiology of natural movement, from thought to intention to action, was preserved. The only addition, as Dr. Courtine described it, was the digital bridge spanning the injured parts of the spine. […] To achieve this result, the researchers first implanted electrodes in Mr. Oskam’s skull and spine. The team then used a machine-learning program to observe which parts of the brain lit up as he tried to move different parts of his body. This thought decoder was able to match the activity of certain electrodes with particular intentions: One configuration lit up whenever Mr. Oskam tried to move his ankles, another when he tried to move his hips.

Then the researchers used another algorithm to connect the brain implant to the spinal implant, which was set to send electrical signals to different parts of his body, sparking movement. The algorithm was able to account for slight variations in the direction and speed of each muscle contraction and relaxation. And, because the signals between the brain and spine were sent every 300 milliseconds, Mr. Oskam could quickly adjust his strategy based on what was working and what wasn’t. Within the first treatment session he could twist his hip muscles. Over the next few months, the researchers fine-tuned the brain-spine interface to better fit basic actions like walking and standing. Mr. Oskam gained a somewhat healthy-looking gait and was able to traverse steps and ramps with relative ease, even after months without treatment. Moreover, after a year in treatment, he began noticing clear improvements in his movement without the aid of the brain-spine interface. The researchers documented these improvements in weight-bearing, balancing and walking tests. Now, Mr. Oskam can walk in a limited way around his house, get in and out of a car and stand at a bar for a drink. For the first time, he said, he feels like he is the one in control.

Source: A Paralyzed Man Can Walk Naturally Again With Brain and Spine Implants – Slashdot