Trained a Convolutional Neural Network (CNN) to solve textual reCAPTCHAs and proposed an active learning technique to overcome the limited amount of available data. Therefore, researchers resorted to DL techniques: However, this technique is not efficient for modern versions since they contain complex backgrounds or overlapping letters. The work in unified this process in a single step method using ML to perform segmentation and recognition and used a “human in the loop” technique to train the character recognizer. This approach was used to solve text-based reCAPTCHAs. The early studies used a two-fold process consisting of a segmentation step followed by a recognition algorithm. Researchers have intensively investigated the security of the reCAPTCHA systems. A score close to 1.0 means that the user is human. This score characterizes the trustability of the user. Google’s reCAPTCHA v3 uses ML to return a risk assessment score between 0.0 and 1.0. On 29 October 2018, the official third version was published and removed any user interface. For example, the authors in designed an AI-based system called UnCAPTCHA to break Google’s most challenging audio reCAPTCHAs. Researchers have also succeeded in hacking these versions using ML and more specifically DL.
As a result, image-based and audio-based reCAPTCHAs were introduced as a second version. with 98% accuracy using ML-based system to segment and recognize the text. This version was defeated by Bursztein et al.
The reCAPTCHA v1 presented a distorted text that the user had to type correctly to pass the test. Previous versions of Google’s reCAPTCHA (v1 and v2) present tasks (images, letters, audio) easily solved by humans but challenging for computers. Its purpose is to protect against automated agents and bots, attacks and spams. Google’s reCAPTCHA system, for detecting bots from humans, is the most used defense mechanism.
0 kommentar(er)
