Precision Profile Pollution Attack on Sequential Recommenders via Influence Function
- URL: http://arxiv.org/abs/2412.01127v1
- Date: Mon, 02 Dec 2024 05:03:56 GMT
- Title: Precision Profile Pollution Attack on Sequential Recommenders via Influence Function
- Authors: Xiaoyu Du, Yingying Chen, Yang Zhang, Jinhui Tang,
- Abstract summary: We introduce an INFluence Function-based Attack approach INFAttack for profile pollution attacks.
We calculate the modifications to the original model using the influence function when generating polluted sequences.
We choose the sequence that has been most significantly influenced to substitute the original sequence, thus promoting the target item.
- Score: 33.7208277448352
- License:
- Abstract: Sequential recommendation approaches have demonstrated remarkable proficiency in modeling user preferences. Nevertheless, they are susceptible to profile pollution attacks (PPA), wherein items are introduced into a user's interaction history deliberately to influence the recommendation list. Since retraining the model for each polluted item is time-consuming, recent PPAs estimate item influence based on gradient directions to identify the most effective attack candidates. However, the actual item representations diverge significantly from the gradients, resulting in disparate outcomes.To tackle this challenge, we introduce an INFluence Function-based Attack approach INFAttack that offers a more accurate estimation of the influence of polluting items. Specifically, we calculate the modifications to the original model using the influence function when generating polluted sequences by introducing specific items. Subsequently, we choose the sequence that has been most significantly influenced to substitute the original sequence, thus promoting the target item. Comprehensive experiments conducted on five real-world datasets illustrate that INFAttack surpasses all baseline methods and consistently delivers stable attack performance for both popular and unpopular items.
Related papers
- Causality-Enhanced Behavior Sequence Modeling in LLMs for Personalized Recommendation [47.29682938439268]
We propose a novel Counterfactual Fine-Tuning (CFT) method to improve user preference modeling.
We employ counterfactual reasoning to identify the causal effects of behavior sequences on model output.
Experiments on real-world datasets demonstrate that CFT effectively improves behavior sequence modeling.
arXiv Detail & Related papers (2024-10-30T08:41:13Z) - Influence Functions for Scalable Data Attribution in Diffusion Models [52.92223039302037]
Diffusion models have led to significant advancements in generative modelling.
Yet their widespread adoption poses challenges regarding data attribution and interpretability.
We develop an influence functions framework to address these challenges.
arXiv Detail & Related papers (2024-10-17T17:59:02Z) - Exploiting Preferences in Loss Functions for Sequential Recommendation via Weak Transitivity [4.7894654945375175]
A choice of optimization objective is immensely pivotal in the design of a recommender system.
We propose a novel method that extends original objectives to explicitly leverage the different levels of preferences as relative orders between their scores.
arXiv Detail & Related papers (2024-08-01T06:55:19Z) - Revisit, Extend, and Enhance Hessian-Free Influence Functions [26.105554752277648]
Influence functions serve as crucial tools for assessing sample influence in model interpretation, subset training set selection, and more.
In this paper, we revisit a specific, albeit effective approximation method known as Trac.
This method substitutes the inverse of the Hessian matrix with an identity matrix.
arXiv Detail & Related papers (2024-05-25T03:43:36Z) - Defending Substitution-Based Profile Pollution Attacks on Sequential
Recommenders [8.828396559882954]
We propose a substitution-based adversarial attack algorithm, which modifies the input sequence by selecting certain vulnerable elements and substituting them with adversarial items.
We also design an efficient adversarial defense method called Dirichlet neighborhood sampling.
In particular, we represent selected items with one-hot encodings and perform gradient ascent on the encodings to search for the worst case linear combination of item embeddings in training.
arXiv Detail & Related papers (2022-07-19T00:19:13Z) - Cross Pairwise Ranking for Unbiased Item Recommendation [57.71258289870123]
We develop a new learning paradigm named Cross Pairwise Ranking (CPR)
CPR achieves unbiased recommendation without knowing the exposure mechanism.
We prove in theory that this way offsets the influence of user/item propensity on the learning.
arXiv Detail & Related papers (2022-04-26T09:20:27Z) - Determinantal Point Process Likelihoods for Sequential Recommendation [12.206748373325972]
We propose two new loss functions based on the Determinantal Point Process (DPP) likelihood, that can be adaptively applied to estimate the subsequent item or items.
Experimental results using the proposed loss functions on three real-world datasets show marked improvements over state-of-the-art sequential recommendation methods in both quality and diversity metrics.
arXiv Detail & Related papers (2022-04-25T11:20:10Z) - Sequential Recommendation via Stochastic Self-Attention [68.52192964559829]
Transformer-based approaches embed items as vectors and use dot-product self-attention to measure the relationship between items.
We propose a novel textbfSTOchastic textbfSelf-textbfAttention(STOSA) to overcome these issues.
We devise a novel Wasserstein Self-Attention module to characterize item-item position-wise relationships in sequences.
arXiv Detail & Related papers (2022-01-16T12:38:45Z) - Deconfounding Scores: Feature Representations for Causal Effect
Estimation with Weak Overlap [140.98628848491146]
We introduce deconfounding scores, which induce better overlap without biasing the target of estimation.
We show that deconfounding scores satisfy a zero-covariance condition that is identifiable in observed data.
In particular, we show that this technique could be an attractive alternative to standard regularizations.
arXiv Detail & Related papers (2021-04-12T18:50:11Z)
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.