Embedding Inference Attack
Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs. Recent works have shown that dense IR system can lead to security vulnerabilities such as embedding inversion attacks. However, such attacks usually require that the attacker knows the embedding model for the attack to be applicable. In this paper, we study IR systems under a black-box setting in which the adversary observes only the unordered set of retrieved documents, without ranking or similarity scores. We demonstrate that in such contexts, tailored queries allow an adversary to identify which embedding model is in use from a set of known model candidate, which we coin as an embedding inference attack (EIA). We also show that certain queries remain discriminative even when the system includes a reranker as a potential defense mechanism. We further validate our method on a real Retrieval-Augmented Generation (RAG) system, in which the tailored queries bypass the LLM's tendency to reject inputs it does not recognize as well-formed questions. Finally, we propose and evaluate other mitigation strategies such as similarity thresholds.
Code (0)
등록된 구현이 없습니다.
Tasks
Information RetrievalSimilar Papers 제목 키워드 기반
Membership Inference on Word Embedding and Beyond
In the text processing context, most ML models are built on word embeddings. These embeddings are themselves trained on some datasets, potentially containing sensitive data. In some cases this training is done independen…
Inference AttackLanguage ModellingMembership Inference AttackText Generation+1User-Level Membership Inference Attack against Metric Embedding Learning
Membership inference (MI) determines if a sample was part of a victim model training set. Recent development of MI attacks focus on record-level membership inference which limits their application in many real-world scen…
Inference AttackMembership Inference AttackPerson Re-IdentificationInference Attacks Against Graph Neural Networks
Graph is an important data representation ubiquitously existing in the real world. However, analyzing the graph data is computationally difficult due to its non-Euclidean nature. Graph embedding is a powerful tool to sol…
Graph ClassificationGraph EmbeddingGraph ReconstructionReconstruction AttackAdversarial Privacy Preserving Graph Embedding against Inference Attack
Recently, the surge in popularity of Internet of Things (IoT), mobile devices, social media, etc. has opened up a large source for graph data. Graph embedding has been proved extremely useful to learn low-dimensional fea…
Graph EmbeddingInference AttackLink PredictionNetwork Embedding+2Image Corruption-Inspired Membership Inference Attacks against Large Vision-Language Models
Large vision-language models (LVLMs) have demonstrated outstanding performance in many downstream tasks. However, LVLMs are trained on large-scale datasets, which can pose privacy risks if training images contain sensiti…