Science Daily June 2, 2021 Researchers at the Pacific Northwest National Laboratory have created a cybersecurity technology called Shadow Figment which uses artificial intelligence to deploy elaborate deception to keep attackers engaged in a pretend world — the figment — that mirrors the real world. The decoy interacts with users in real time, responding in realistic ways to commands. It rewards hackers with false signals of success, keeping them occupied while defenders learn about the attackers’ methods and take actions to protect the real system. The credibility of the deception relies on a machine learning program that learns from observing […]
Tag Archives: Cyber-attack
Attackers could be listening to what you type
Science Daily August 14, 2019 Researchers at the Southern Methodist University investigate the capability of mobile phone sensor arrays, using audio and motion sensor data, for classifying keystrokes that occur on a keyboard in proximity to phones around a table, as would be common in a meeting. They developed a system of mixed convolutional and recurrent neural networks and deployed the system in a human subjects experiment with 20 users typing naturally while talking. Using leave-one-user-out cross validation, they found that mobile phone arrays have the ability to detect 41.8% of keystrokes and 27% of typed words correctly in such […]
Why did my classifier just mistake a turtle for a rifle?
MIT News July 31, 2019 We know instinctively that people and machines see the world differently, but the paper showed that the difference could be isolated and measured. Researchers at MIT have shown that a computer vision model could be compromised in a so-called black-box attack by simply feeding it progressively altered images until one caused the system to fail. Recently they highlighted multiple cases in which classifiers could be duped into confusing cats and skiers for guacamole and dogs, respectively. They trained a model to identify cats based on “robust” features recognizable to humans, and “non-robust” features that humans […]
New computer attack mimics user’s keystroke characteristics and evades detection
Science Daily June 6, 2019 Researchers in Israel have developed a new attack called Malboard and a detection module. Malboard automatically generates keystrokes that have the attacked user’s behavioral characteristics. The keystrokes are injected into the computer in the form of malicious commands and thus can evade existing detection mechanisms designed to continuously verify the user’s identity based on keystroke dynamics. In demonstration attack against three existing detection mechanisms, the results showed that Malboard managed to evade detection in 83–100% of the cases, depending on the detection tools in place. They also developed three different modules, aimed at detecting keystroke […]