Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher

Abstract

Machine unlearning has become an important field of research due to an increasing focus on addressing the evolving data privacy rules and regulations into the machine learning (ML) applications. It facilitates the request for removal of certain set or class of data from the already trained ML model without retraining from scratch. Recently, several efforts have been made to perform unlearning in an effective and efficient manner. We propose a novel machine unlearning method by exploring the utility of competent and incompetent teachers in a student-teacher framework to induce forgetfulness. The knowledge from the competent and incompetent teachers is selectively transferred to the student to obtain a model that doesn't contain any information about the forget data. We experimentally show that this method is well generalized, fast, and effective. Furthermore, we introduce a zero retrain forgetting (ZRF) metric to evaluate the unlearning method. Unlike the existing unlearning metrics, the ZRF score does not depend on the availability of the expensive retrained model. This makes it useful for analysis of the unlearned model after deployment as well. The experiments are conducted for random subset forgetting and class forgetting on various deep networks and across different application domains. A use case of forgetting information about the patients' medical records is also presented. The source code will be made publicly available.

Audit to Forget: A Unified Method to Revoke Patients’ Private Data in Intelligent Healthcare

“…Once the data of certain patients is confirmed to be used to train the target DL model by auditing, forgetting requires the removal of learnt information of certain patients' data from the target DL model, which is also called machine unlearning, while auditing could act as the verification of machine unlearning [18] In order to achieve forgetting, existing unlearning methods could be classified into three major classes, including model-agnostic methods, model-intrinsic methods and data-driven methods [20]. Model-agnostic methods refer to algorithms or frameworks that can be used for different DL models, including differential privacy [18], [21], [22], certified removal [23], [24], [25], statistical query learning [6], decremental learning [26], knowledge adaptation [27], [28] and parameter sampling [29]. Model-intrinsic approaches are those methods designed for specific types of models, such as for softmax classifiers [30], linear models [31], treebased models [32] and Bayesian models [19].…”

“…When forgetting is accomplished, auditing is the next necessary step to verify it. Different metrics have been proposed to audit the membership of the query dataset, including accuracy, completeness [6], unlearn time, relearn time, retrain time, layer-wise distance, activation distance, JS-divergence, membership inference [37], [38], ZRF score [27], epistemic uncertainty [39] and model inversion attack [7]. In recent studies, membership inference-based metrics were frequently utilized to determine whether or not any information about the samples to be forgotten was retained in the model in intelligent healthcare [38].…”