Attacks against Ranking Algorithms with Text Embeddings: a Case Study on Recruitment Algorithms
Recently, some studies have shown that text classification tasks are vulnerable to poisoning and evasion attacks. However, little work has investigated attacks against decision making algorithms that use text embeddings, and their output is a ranking. In this paper, we focus on ranking algorithms for recruitment process, that employ text embeddings for ranking applicants resumes when compared to a job description. We demonstrate both white box and black box attacks that identify text items, that based on their location in embedding space, have significant contribution in increasing the similarity score between a resume and a job description. The adversary then uses these text items to improve the ranking of their resume among others. We tested recruitment algorithms that use the similarity scores obtained from Universal Sentence Encoder (USE) and Term Frequency Inverse Document Frequency (TF IDF) vectors. Our results show that in both adversarial settings, on average the attacker is successful. We also found that attacks against TF IDF is more successful compared to USE.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingSentencetext-classificationText ClassificationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models
Recent research has shown that neural information retrieval techniques may be susceptible to adversarial attacks. Adversarial attacks seek to manipulate the ranking of documents, with the intention of exposing users to t…
Adversarial TextInformation RetrievalRe-RankingSentence+1Affect Enriched Word Embeddings for News Information Retrieval
Distributed representations of words have shown to be useful to improve the effectiveness of IR systems in many sub-tasks like query expansion, retrieval and ranking. Algorithms like word2vec, GloVe and others are also k…
Information RetrievalRetrievalWord EmbeddingsRevisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective
Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primaril…
Adversarial DefenseAdversarial RobustnessAdversarial TextUntargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense
Federated recommendation (FedRec) can train personalized recommenders without collecting user data, but the decentralized nature makes it susceptible to poisoning attacks. Most previous studies focus on the targeted atta…
Contrastive LearningRecommendation SystemsAdversarial Attack and Defense in Deep Ranking
Deep Neural Network classifiers are vulnerable to adversarial attack, where an imperceptible perturbation could result in misclassification. However, the vulnerability of DNN-based image ranking systems remains under-exp…
Adversarial AttackAdversarial RobustnessTriplet