MSAP: Multi-Step Adversarial Perturbations on Recommender Systems Embeddings
نویسندگان
چکیده
Recommender systems (RSs) have attained exceptional performance in learning users' preferences and finding the most suitable products. Recent advances adversarial machine (AML) computer vision raised interests recommenders' security.It has been demonstrated that widely adopted model-based recommenders, e.g., BPR-MF, are not robust to perturbations added on learned parameters, embeddings, which can cause drastic reduction of recommendation accuracy.However, state-of-the-art method, named fast gradient sign method (FGSM), builds perturbation with a single-step procedure. In this work, we extend FGSM proposing multi-step (MSAP) procedures study robustness under powerful methods. Letting fixed magnitude, illustrate MSAP is much more harmful than corrupting BPR-MF. Then, assess efficacy robustified version i.e., AMF. Finally, analyze variations fairness measurements each perturbed recommender. Code data available at https://github.com/sisinflab/MSAP.
منابع مشابه
On Detecting Adversarial Perturbations
Machine learning and deep learning in particular has advanced tremendously on perceptual tasks in recent years. However, it remains vulnerable against adversarial perturbations of the input that have been crafted specifically to fool the system while being quasi-imperceptible to a human. In this work, we propose to augment deep neural networks with a small “detector” subnetwork which is trained...
متن کاملEvaluation of recommender systems: A multi-criteria decision making approach
The evaluation and selection of recommender systems is a difficult decision making process. This difficulty is partially due to the large diversity of published evaluation criteria in addition to lack of standardized methods of evaluation. As such, a systematic methodology is needed that explicitly considers multiple, possibly conflicting metrics and assists decision makers to evaluate and find...
متن کاملMulti-Criteria Recommender Systems
This chapter aims to provide an overview of the class of multi-criteria recommender systems. First, it defines the recommendation problem as a multicriteria decision making (MCDM) problem, and reviews MCDM methods and techniques that can support the implementation of multi-criteria recommenders. Then, it focuses on the category of multi-criteria rating recommenders – techniques that provide rec...
متن کاملGenerative Adversarial Perturbations
In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for transforming images to adversarial perturbations. Our proposed models can produce image-agnostic and image-dependent perturbations for targeted and nontargeted at...
متن کاملevaluation of recommender systems: a multi-criteria decision making approach
the evaluation and selection of recommender systems is a difficult decision making process. this difficulty is partially due to the large diversity of published evaluation criteria in addition to lack of standardized methods of evaluation. as such, a systematic methodology is needed that explicitly considers multiple, possibly conflicting metrics and assists decision makers to evaluate and find...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Proceedings of the ... International Florida Artificial Intelligence Research Society Conference
سال: 2021
ISSN: ['2334-0762', '2334-0754']
DOI: https://doi.org/10.32473/flairs.v34i1.128443