The Guardian is right to oppose automated facial recognition (Editorial, 10 June), but in spite of concerns from MPs and peers, parliament has hardly discussed the issue. As the person who organised the only debate on the subject in the House of Lords, I have started legal action against the police for failing to have a regulatory framework for its use. It's shocking that we are allowing the police and companies to set the rules as we abolish privacy in public spaces, because ministers are failing to act. The difference between ourselves and the likes of China and Russia is that we have a fairly open democracy, but this is no defence against state oppression and commercial exploitation if politicians fail to recognise that when our face becomes an identity card, all the rules change. Click here to upload it and we'll publish the best submissions in the letters spread of our print edition

Deepfakes are video manipulations that can make people say seemingly strange things. Barack Obama and Nicolas Cage have been featured in these videos. Facebook's misinformation policies are being put to the test. A deepfake video of CEO Mark Zuckerberg recently surfaced on Facebook-owned Instagram, and reportedly the social networking site has chosen to leave it up, for now. The video appears to show Zuckerberg saying things he never actually said.

Deep fakes are "videos that have been constructed to make a person appear to say or do something that they never said or did. Many commentators worry that voters will be influenced by pure fiction: As the 2020 US election looms, we learn of the fight to stay ahead (CNN, April 26, 2019) of the "growing threat" (ABC Eyewitness News, May 7, 2019) because "The 2020 campaigns aren't ready for deepfakes" (Axios/HBO, June 4, 2019). We Can No Longer Believe What We See, the New York Times warned yesterday. Under the right set of circumstances, deepfakes will be very influential. They don't even have to be particularly good to potentially swing the outcome of an election. As with so much in elections, deepfakes are a numbers game. While the presence of tampering in all but the most sophisticated deepfakes can be quickly identified, not everyone who views them will get that message. More fundamentally, not everyone wants to get that message. As can occur with other forms of online ...

Highlighting the company's rapid progress in the radiology space, Israeli startup Aidoc has received its third FDA clearance for its AI-based algorithm to help highlight potential instances of cervical spinal fractures. The regulatory decision comes just a few weeks after the FDA cleared the company's pulmonary embolism product. Aidoc also has approval for its algorithm for the detection of intracranial hemorrhages through CT scans. The company's cervical spinal fracture product already received approval from European regulators. Delayed diagnosis of cervical spinal fracture is a common problem in emergency rooms and can lead to potential major neurological issues including quadriplegia.

Two artists and an advertising company created a deepfake of Facebook founder Mark Zuckerberg saying things he never said, and uploaded it to Instagram. The video, created by artists Bill Posters and Daniel Howe in partnership with advertising company Canny, shows Mark Zuckerberg sitting at a desk, seemingly giving a sinister speech about Facebook's power. The video is framed with broadcast chyrons that say "We're increasing transparency on ads," to make it look like it's part of a news segment. "Imagine this for a second: One man, with total control of billions of people's stolen data, all their secrets, their lives, their futures," Zuckerberg's likeness says, in the video. "I owe it all to Spectre. Spectre showed me that whoever controls the data, controls the future."

A couple of artists teamed up with an advertising company to make the deepfake video of Mark Zuckerberg. The video on Instagram shows what appears to be Facebook CEO Mark Zuckerberg giving a brief speech about the power of big data. "Imagine this for a second: One man, with total control of billions of people's stolen data, all their secrets, their lives, their futures. I owe it all to Spectre. Spectre showed me that whoever controls the data, controls the future."

According to a survey conducted by Senseon as part of a research project on Small and Medium-sized Enterprises (SMEs), 81 percent of participants believe that AI would improve the future of cybersecurity while only 3 percent disagree. The remaining 16 percent stated that they were uncertain. Due to how innovative AI has become over the past few years, it is reasonable that the survey generated such a result. The question is, how does the aspect of machine intelligence provide benefits to the company and what objectives and initiatives must the developer, analyst and decision maker establish to enable those types of AI to benefit the security of the cyber age? The Microsoft Vice-President of Cybersecurity Solutions Group, Ann Johnson, told the RTE News during a meeting in Dublin that she sees about six and a half trillion cyber threats that Microsoft receive every day.

DUBAI, UNITED ARAB EMIRATES - Yemen's Houthi rebels said on Tuesday they launched at least two drones targeting a southwest Saudi city that's home to an air base. The Houthis' Al-Masirah satellite news channel reported the rebels launched Qasef-2K drones to strike the city of Khamis Mushait. The state-run Saudi Press Agency reported Tuesday, quoting military spokesman Col. Turki al-Maliki, that soldiers "intercepted" two drones launched by the Houthis. The Iranian-allied Houthis increasingly have targeted the kingdom with bomb-carrying drones. Khamis Mushait, some 815 km (510 miles) southwest of the capital, Riyadh, is near the kingdom's border with Yemen.

For many structured learning tasks, the data annotation process is complex and costly. Existing annotation schemes usually aim at acquiring completely annotated structures, under the common perception that partial structures are of low quality and could hurt the learning process. This paper questions this common perception, motivated by the fact that structures consist of interdependent sets of variables. Thus, given a fixed budget, partly annotating each structure may provide the same level of supervision, while allowing for more structures to be annotated. We provide an information theoretic formulation for this perspective and use it, in the context of three diverse structured learning tasks, to show that learning from partial structures can sometimes outperform learning from complete ones. Our findings may provide important insights into structured data annotation schemes and could support progress in learning protocols for structured tasks.

Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. Here, we instead view adversarial attacks as a generative modelling problem, with the goal of producing entire distributions of adversarial examples given an unperturbed input. We show that this generative perspective can be used to design a unified encoder-decoder framework, which is domain-agnostic in that the same framework can be employed to attack different domains with minimal modification. Across three diverse domains---images, text, and graphs---our approach generates whitebox attacks with success rates that are competitive with or superior to existing approaches, with a new state-of-the-art achieved in the graph domain. Finally, we demonstrate that our generative framework can efficiently generate a diverse set of attacks for a single given input, and is even capable of attacking unseen test instances in a zero-shot manner, exhibiting attack generalization.