--- title: "An AI “Vaccine” Can Block Adversarial Attacks" description: "Scientists developed an AI \"vaccine\" that can make algorithms more resistant to hackers who launch adversarial attacks to try and confuse the systems." date: "2019-06-20" modified: "2019-06-20" authors: - name: "Dan Robitzski" link: "https://futurism.com/authors/danrobitzski" url: "https://futurism.com/the-byte/ai-vaccine-block-adversarial-attacks" categories: - "Artificial Intelligence" tags: - "adversarial attacks" - "artificial intelligence" - "the digest" --- # An AI “Vaccine” Can Block Adversarial Attacks ![Scientists developed an AI "vaccine" that can make algorithms more resistant to hackers who launch adversarial attacks to try and confuse the systems.]() *\Image: Victor Tangermann\* ## Virtual Vaccine For as smart as artificial intelligence systems seem to get, they're still easily confused by hackers who launch so-called adversarial attacks — cyberattacks that trick algorithms into misinterpreting their training data, sometimes to disastrous ends. In order to [bolster AI's defenses]() from these dangerous hacks, scientists at the Australian research agency CSIRO [say in a press release]() they've created a sort of AI "vaccine" that trains algorithms on weak adversaries so they're better prepared for the real thing — not entirely unlike how vaccines expose our immune systems to inert viruses so they can fight off infections in the future. ## Get Your Shots CSIRO found that AI systems like those that steer self-driving cars could [easily be tricked]() into thinking that a stop sign on the side of the road was actually a speed limit sign, a particularly dangerous example of how adversarial attacks could cause harm. The scientists developed a way to distort the training data fed into an AI system so that it isn't as easily fooled later on, [according to research]() presented at the [International Conference on Machine Learning]() last week. "We implement a weak version of an adversary, such as small modifications or distortion to a collection of images, to create a more 'difficult' training data set," Richard Nock, head of machine learning at CSIRO, said in the press release. "When the algorithm is trained on data exposed to a small dose of distortion, the resulting model is more robust and immune to adversarial attacks." READ MORE: [Researchers develop 'vaccine' against attacks on machine learning]() \[CSIRO newsroom\] More on adversarial attacks: *[To Build Trust In Artificial Intelligence, IBM Wants Developers To Prove Their Algorithms Are Fair]()* ## Author Dan Robitzki is a senior reporter for Futurism, where he likes to cover AI, tech ethics, and medicine. He spends his extra time fencing and streaming games from Los Angeles, California. ### Author social links [Twitter]()