Sentence examples for dishonest recommendations from inspiring English sources

Therefore, a mechanism to avoid the influence of dishonest recommendations from malicious recommenders is a fundamental problem for trust models.

Even when the percentage of dishonest recommenders is 48%, the detection rate is higher than 70%, whereas the base model is unable to detect all dishonest recommenders even when the percentage of dishonest recommendations is as low as 10%.

In the literature, many approaches have been proposed to evaluate accurate recommended trust value in the presence of dishonest recommendations.

It has already been established that dishonest recommendations are difficult to detect when either the percentage of the dishonest recommenders is high or the MO level is very low.

A smart attacker may behave well for a while to get a high reputation and then provide all dishonest recommendations that cannot be detected by schemes using reputation[15], that is, a recommender can build reputation with different expectations and intentions, and the recommendation they provide can be different from their experience.

Let us suppose that the service provider asks for recommendations regarding an unknown service requester A. In this experiment we assume that a certain percentage of the recommenders are dishonest and launch a BM attack against (A) by giving dishonest recommendations.

In this case, the bias introduced by the undetected dishonest recommendation in recommended trust value (0.25−0.2 = 0.05) is a very low value and does not have much impact on the final recommended trust value.

Thus, all three approaches ([25, 26], and[23]) fail to achieve perfect filtering of dishonest recommendation as the percentage of dishonest recommenders increases.

It relies only on the recommendations provided by the recommender to detect dishonest recommendation.

The recommenders can falsely provide dishonest recommendation either to elevate trust values of malicious entities or to lessen the trust values of honest entities.

It will assign low recommendation trust to the recommending service believing that that it has sent dishonest recommendation.