paper-with-me

Papers

CtrlRAG: Black-box Adversarial Attacks Based on Masked Language Models in Retrieval-Augmented Language Generation

2025-03-10 · Runqi Sui

Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) by integrating external knowledge bases. However, this integration introduces a new security threat: adversaries can exploit the retrieval mechanism to inject malicious content into the knowledge base, thereby influencing the generated responses. Based on this attack vector, we propose CtrlRAG, a novel attack method designed for RAG system in the black-box setting, which aligns with real-world scenarios. Unlike existing attack methods, CtrlRAG introduces a perturbation mechanism using Masked Language Model (MLM) to dynamically optimize malicious content in response to changes in the retrieved context. Experimental results demonstrate that CtrlRAG outperforms three baseline methods in both Emotional Manipulation and Hallucination Amplification objectives. Furthermore, we evaluate three existing defense mechanisms, revealing their limited effectiveness against CtrlRAG and underscoring the urgent need for more robust defenses.

📄 PDF Abstract BibTeX arXiv:2503.06950

Code (0)

등록된 구현이 없습니다.

Tasks

HallucinationLanguage ModelingLanguage ModellingRAGRetrievalRetrieval-augmented GenerationText Generation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.

Similar Papers 제목 키워드 기반

A Context Aware Approach for Generating Natural Language Attacks

2020-12-24 · Rishabh Maheshwary, Saket Maheshwary, Vikram Pudi

We study an important task of attacking natural language processing models in a black box setting. We propose an attack strategy that crafts semantically similar adversarial examples on text classification and entailment…

Language ModellingSentencetext-classificationText Classification

Improving Robustness of Facial Landmark Detection by Defending Against Adversarial Attacks

2021-01-01 · ICCV 2021 10 · Congcong Zhu, Xiaoqiang Li, Jide Li, Songmin Dai

Many recent developments in facial landmark detection have been driven by stacking model parameters or augmenting annotations. However, three subsequent challenges remain, including 1) an increase in computational ov…

Face AlignmentFacial Landmark Detection

Text Adversarial Purification as Defense against Adversarial Attacks

2022-03-27 · Linyang Li, Demin Song, Xipeng Qiu

Adversarial purification is a successful defense mechanism against adversarial attacks without requiring knowledge of the form of the incoming attack. Generally, adversarial purification aims to remove the adversarial pe…

Adversarial AttackAdversarial DefenseAdversarial Purification

Arabic Synonym BERT-based Adversarial Examples for Text Classification

2024-02-05 · Norah Alshahrani, Saied Alshahrani, Esma Wali, Jeanna Matthews

Text classification systems have been proven vulnerable to adversarial text examples, modified versions of the original text examples that are often unnoticed by human eyes, yet can force text classification models to al…

Adversarial TextLanguage ModelingLanguage ModellingMasked Language Modeling+2

Masked Language Model Based Textual Adversarial Example Detection

2023-04-18 · Xiaomei Zhang, Zhaoxi Zhang, Qi Zhong, Xufei Zheng 외

Adversarial attacks are a serious threat to the reliable deployment of machine learning models in safety-critical applications. They can misguide current models to predict incorrectly by slightly modifying the inputs. Re…

Adversarial DefenseLanguage ModelingLanguage ModellingSST-2