Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks

• URL: http://arxiv.org/abs/2501.16902v1
• Date: Tue, 28 Jan 2025 12:40:37 GMT
• Title: Document Screenshot Retrievers are Vulnerable to Pixel Poisoning Attacks
• Authors: Shengyao Zhuang, Ekaterina Khramtsova, Xueguang Ma, Bevan Koopman, Jimmy Lin, Guido Zuccon,
• Abstract summary: Vision-language model (VLM)-based retrievers leverage document screenshots embedded as vectors to enable effective search and offer a simplified pipeline over traditional text-only methods. In this study, we propose three pixel poisoning attack methods designed to compromise VLM-based retrievers.
• Score: 72.4498910775871
• License:
• Abstract: Recent advancements in dense retrieval have introduced vision-language model (VLM)-based retrievers, such as DSE and ColPali, which leverage document screenshots embedded as vectors to enable effective search and offer a simplified pipeline over traditional text-only methods. In this study, we propose three pixel poisoning attack methods designed to compromise VLM-based retrievers and evaluate their effectiveness under various attack settings and parameter configurations. Our empirical results demonstrate that injecting even a single adversarial screenshot into the retrieval corpus can significantly disrupt search results, poisoning the top-10 retrieved documents for 41.9% of queries in the case of DSE and 26.4% for ColPali. These vulnerability rates notably exceed those observed with equivalent attacks on text-only retrievers. Moreover, when targeting a small set of known queries, the attack success rate raises, achieving complete success in certain cases. By exposing the vulnerabilities inherent in vision-language models, this work highlights the potential risks associated with their deployment.

Related papers

• Illusions of Relevance: Using Content Injection Attacks to Deceive Retrievers, Rerankers, and LLM Judges [52.96987928118327]
  We find that embedding models for retrieval, rerankers, and large language model (LLM) relevance judges are vulnerable to content injection attacks. We identify two primary threats: (1) inserting unrelated or harmful content within passages that still appear deceptively "relevant", and (2) inserting entire queries or key query terms into passages to boost their perceived relevance. Our study systematically examines the factors that influence an attack's success, such as the placement of injected content and the balance between relevant and non-relevant material.
  arXiv  Detail & Related papers  (2025-01-30T18:02:15Z)
• GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search [2.30419421321987]
  embedding-based text retrievalx2013$retrieval of relevant passages from corpora via deep encodings$corporax2013$has emerged as a powerful method state-of-the-art search results and popular the use of Augmented Retrieval Generation (RAG)
  arXiv  Detail & Related papers  (2024-12-30T13:49:28Z)
• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• Corpus Poisoning via Approximate Greedy Gradient Descent [48.5847914481222]
  We propose Approximate Greedy Gradient Descent, a new attack on dense retrieval systems based on the widely used HotFlip method for generating adversarial passages. We show that our method achieves a high attack success rate on several datasets and using several retrievers, and can generalize to unseen queries and new domains.
  arXiv  Detail & Related papers  (2024-06-07T17:02:35Z)
• Whispers in Grammars: Injecting Covert Backdoors to Compromise Dense Retrieval Systems [40.131588857153275]
  This paper investigates a novel attack scenario where the attackers aim to mislead the retrieval system into retrieving the attacker-specified contents. Those contents, injected into the retrieval corpus by attackers, can include harmful text like hate speech or spam. Unlike prior methods that rely on model weights and generate conspicuous, unnatural outputs, we propose a covert backdoor attack triggered by grammar errors.
  arXiv  Detail & Related papers  (2024-02-21T05:03:07Z)
• Poisoning Retrieval Corpora by Injecting Adversarial Passages [79.14287273842878]
  We propose a novel attack for dense retrieval systems in which a malicious user generates a small number of adversarial passages. When these adversarial passages are inserted into a large retrieval corpus, we show that this attack is highly effective in fooling these systems. We also benchmark and compare a range of state-of-the-art dense retrievers, both unsupervised and supervised.
  arXiv  Detail & Related papers  (2023-10-29T21:13:31Z)
• QAIR: Practical Query-efficient Black-Box Attacks for Image Retrieval [56.51916317628536]
  We study the query-based attack against image retrieval to evaluate its robustness against adversarial examples under the black-box setting. A new relevance-based loss is designed to quantify the attack effects by measuring the set similarity on the top-k retrieval results before and after attacks. Experiments show that the proposed attack achieves a high attack success rate with few queries against the image retrieval systems under the black-box setting.
  arXiv  Detail & Related papers  (2021-03-04T10:18:43Z)

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.