Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System

• URL: http://arxiv.org/abs/2409.17476v1
• Date: Thu, 26 Sep 2024 02:24:03 GMT
• Title: Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
• Authors: Kaike Zhang, Qi Cao, Yunfan Wu, Fei Sun, Huawei Shen, Xueqi Cheng,
• Abstract summary: Vulnerability-aware Adversarial Training (VAT) is designed to defend against poisoning attacks in recommender systems. VAT employs a novel vulnerability-aware function to estimate users' vulnerability based on the degree to which the system fits them.
• Score: 60.719158008403376
• License:
• Abstract: Recommender systems play a pivotal role in mitigating information overload in various fields. Nonetheless, the inherent openness of these systems introduces vulnerabilities, allowing attackers to insert fake users into the system's training data to skew the exposure of certain items, known as poisoning attacks. Adversarial training has emerged as a notable defense mechanism against such poisoning attacks within recommender systems. Existing adversarial training methods apply perturbations of the same magnitude across all users to enhance system robustness against attacks. Yet, in reality, we find that attacks often affect only a subset of users who are vulnerable. These perturbations of indiscriminate magnitude make it difficult to balance effective protection for vulnerable users without degrading recommendation quality for those who are not affected. To address this issue, our research delves into understanding user vulnerability. Considering that poisoning attacks pollute the training data, we note that the higher degree to which a recommender system fits users' training data correlates with an increased likelihood of users incorporating attack information, indicating their vulnerability. Leveraging these insights, we introduce the Vulnerability-aware Adversarial Training (VAT), designed to defend against poisoning attacks in recommender systems. VAT employs a novel vulnerability-aware function to estimate users' vulnerability based on the degree to which the system fits them. Guided by this estimation, VAT applies perturbations of adaptive magnitude to each user, not only reducing the success ratio of attacks but also preserving, and potentially enhancing, the quality of recommendations. Comprehensive experiments confirm VAT's superior defensive capabilities across different recommendation models and against various types of attacks.

Related papers

• Rethinking the Vulnerabilities of Face Recognition Systems:From a Practical Perspective [53.24281798458074]
  Face Recognition Systems (FRS) have increasingly integrated into critical applications, including surveillance and user authentication. Recent studies have revealed vulnerabilities in FRS to adversarial (e.g., adversarial patch attacks) and backdoor attacks (e.g., training data poisoning)
  arXiv  Detail & Related papers  (2024-05-21T13:34:23Z)
• Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought [43.490918008927]
  We propose shadow-free MIAs that directly leverage a user's recommendations for membership inference. Our attack achieves far better attack accuracy with low false positive rates than baselines.
  arXiv  Detail & Related papers  (2024-05-11T13:52:22Z)
• Poisoning Federated Recommender Systems with Fake Users [48.70867241987739]
  Federated recommendation is a prominent use case within federated learning, yet it remains susceptible to various attacks. We introduce a novel fake user based poisoning attack named PoisonFRS to promote the attacker-chosen targeted item. Experiments on multiple real-world datasets demonstrate that PoisonFRS can effectively promote the attacker-chosen item to a large portion of genuine users.
  arXiv  Detail & Related papers  (2024-02-18T16:34:12Z)
• Poisoning Deep Learning based Recommender Model in Federated Learning Scenarios [7.409990425668484]
  We design attack approaches targeting deep learning based recommender models in federated learning scenarios. Our well-designed attacks can effectively poison the target models, and the attack effectiveness sets the state-of-the-art.
  arXiv  Detail & Related papers  (2022-04-26T15:23:05Z)
• PipAttack: Poisoning Federated Recommender Systems forManipulating Item Promotion [58.870444954499014]
  A common practice is to subsume recommender systems under the decentralized federated learning paradigm. We present a systematic approach to backdooring federated recommender systems for targeted item promotion.
  arXiv  Detail & Related papers  (2021-10-21T06:48:35Z)
• Membership Inference Attacks Against Recommender Systems [33.66394989281801]
  We make the first attempt on quantifying the privacy leakage of recommender systems through the lens of membership inference. Our attack is on the user-level but not on the data sample-level. A shadow recommender is established to derive the labeled training data for training the attack model.
  arXiv  Detail & Related papers  (2021-09-16T15:19:19Z)
• Adversarial defense for automatic speaker verification by cascaded self-supervised learning models [101.42920161993455]
  More and more malicious attackers attempt to launch adversarial attacks at automatic speaker verification (ASV) systems. We propose a standard and attack-agnostic method based on cascaded self-supervised learning models to purify the adversarial perturbations. Experimental results demonstrate that the proposed method achieves effective defense performance and can successfully counter adversarial attacks.
  arXiv  Detail & Related papers  (2021-02-14T01:56:43Z)
• Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verification [78.51092318750102]
  This work proposes to defend ASV systems against adversarial attacks with a separate detection network. A VGG-like binary classification detector is introduced and demonstrated to be effective on detecting adversarial samples.
  arXiv  Detail & Related papers  (2020-06-11T04:31:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.