paper-with-me

Papers

Query Obfuscation by Semantic Decomposition

2022-06-01 · LREC 2022 6 · Danushka Bollegala, Tomoya Machide, Ken-ichi Kawarabayashi

We propose a method to protect the privacy of search engine users by decomposing the queries using semantically related and unrelated distractor terms. Instead of a single query, the search engine receives multiple decomposed query terms. Next, we reconstruct the search results relevant to the original query term by aggregating the search results retrieved for the decomposed query terms. We show that the word embeddings learnt using a distributed representation learning method can be used to find semantically related and distractor query terms. We derive the relationship between the obfuscity achieved through the proposed query anonymisation method and the reconstructability of the original search results using the decomposed queries. We analytically study the risk of discovering the search engine users’ information intents under the proposed query obfuscation method, and empirically evaluate its robustness against clustering-based attacks. Our experimental results show that the proposed method can accurately reconstruct the search results for user queries, without compromising the privacy of the search engine users.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningWord Embeddings

Similar Papers 제목 키워드 기반

Query Obfuscation Semantic Decomposition

2019-09-12 · Danushka Bollegala, Tomoya Machide, Ken-ichi Kawarabayashi

We propose a method to protect the privacy of search engine users by decomposing the queries using semantically \emph{related} and unrelated \emph{distractor} terms. Instead of a single query, the search engine receives …

ClusteringInformation RetrievalRepresentation LearningWord Embeddings

A Systematic Exploration of Text Decomposition and Budget Distribution in Differentially Private Text Obfuscation

2026-05-01 · Stephen Meisenbacher, Angelo Kleinert, Florian Matthes arxiv

The goal of differentially private text obfuscation is to obfuscate, or "perturb", input texts with Differential Privacy (DP) guarantees, such that the private output texts are quantifiably indistinguishable from the ori…

Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddings

2021-10-16 · ACL ARR October 2021 10 · Anonymous

We propose a method to protect the privacy of search engine users by decomposing the queries using semantically \emph{related} and unrelated \emph{distractor} terms. Instead of a single query, the search engine receives …

Representation LearningWord Embeddings

WordGame: Efficient & Effective LLM Jailbreak via Simultaneous Obfuscation in Query and Response

2024-05-22 · Tianrong Zhang, Bochuan Cao, Yuanpu Cao, Lu Lin 외

The recent breakthrough in large language models (LLMs) such as ChatGPT has revolutionized production processes at an unprecedented pace. Alongside this progress also comes mounting concerns about LLMs' susceptibility to…

LLM JailbreakSafety Alignment

ALISON: Fast and Effective Stylometric Authorship Obfuscation

2024-02-01 · Eric Xing, Saranya Venkatraman, Thai Le, Dongwon Lee

Authorship Attribution (AA) and Authorship Obfuscation (AO) are two competing tasks of increasing importance in privacy research. Modern AA leverages an author's consistent writing style to match a text to its author usi…

Authorship Attribution