English
Related papers

Related papers: Fight Poison with Poison: Enhancing Robustness in …

200 papers

Retrieval-Augmented Generation (RAG) systems have emerged as a promising solution to mitigate LLM hallucinations and enhance their performance in knowledge-intensive domains. However, these systems are vulnerable to adversarial poisoning…

Information Retrieval · Computer Science 2025-07-29 Jinyan Su , Jin Peng Zhou , Zhengxin Zhang , Preslav Nakov , Claire Cardie

Knowledge poisoning poses a critical threat to Retrieval-Augmented Generation (RAG) systems by injecting adversarial content into knowledge bases, tricking Large Language Models (LLMs) into producing attacker-controlled outputs grounded in…

Computation and Language · Computer Science 2026-05-18 Yutao Wu , Xiao Liu , Yinghui Li , Yifeng Gao , Yifan Ding , Jiale Ding , Xiang Zheng , Xingjun Ma

Machine-generated Text (MGT) detection is crucial for regulating and attributing online texts. While the existing MGT detectors achieve strong performance, they remain vulnerable to simple perturbations and adversarial attacks. To build an…

Cryptography and Security · Computer Science 2025-05-01 Yuanfan Li , Zhaohan Zhang , Chengzhengxu Li , Chao Shen , Xiaoming Liu

We explore adversarial attacks against retrieval-augmented generation (RAG) systems to identify their vulnerabilities. We focus on generating human-imperceptible adversarial examples and introduce a novel imperceptible retrieve-to-generate…

Information Retrieval · Computer Science 2025-05-29 Hongru Song , Yu-an Liu , Ruqing Zhang , Jiafeng Guo , Jianming Lv , Maarten de Rijke , Xueqi Cheng

Retrieval-augmented generation (RAG) is increasingly deployed in real-world applications, where its reference-grounded design makes outputs appear trustworthy. This trust has spurred research on poisoning attacks that craft malicious…

Cryptography and Security · Computer Science 2026-02-09 Haoyang Hu , Zhejun Jiang , Yueming Lyu , Junyuan Zhang , Yi Liu , Ka-Ho Chow

We study backdoor poisoning attacks against image classification networks, whereby an attacker inserts a trigger into a subset of the training data, in such a way that at test time, this trigger causes the classifier to predict some target…

Cryptography and Security · Computer Science 2022-02-03 Muhammad Usman , Youcheng Sun , Divya Gopinath , Corina S. Pasareanu

Few-shot classifiers have been shown to exhibit promising results in use cases where user-provided labels are scarce. These models are able to learn to predict novel classes simply by training on a non-overlapping set of classes. This can…

Machine Learning · Computer Science 2021-10-26 Yi Xiang Marcus Tan , Penny Chong , Jiamei Sun , Ngai-man Cheung , Yuval Elovici , Alexander Binder

Few-shot classification with foundation models (e.g., CLIP, DINOv2, PaLM-2) enables users to build an accurate classifier with a few labeled training samples (called support samples) for a classification task. However, an attacker could…

Cryptography and Security · Computer Science 2024-04-15 Yanting Wang , Wei Zou , Jinyuan Jia

Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low corruption rates. We show that existing attacks are not designed to be stealthy, allowing reliable…

Cryptography and Security · Computer Science 2026-05-25 Sarthak Choudhary , Nils Palumbo , Ashish Hooda , Krishnamurthy Dj Dvijotham , Somesh Jha

Retrieval-Augmented Generation (RAG) has emerged as a powerful approach to boost the capabilities of large language models (LLMs) by incorporating external, up-to-date knowledge sources. However, this introduces a potential vulnerability to…

Machine Learning · Computer Science 2026-03-30 Kennedy Edemacu , Vinay M. Shashidhar , Micheal Tuape , Dan Abudu , Beakcheol Jang , Jong Wook Kim

Transformer-based text classifiers such as BERT, RoBERTa, T5, and GPT have shown strong performance in natural language processing tasks but remain vulnerable to adversarial examples. These vulnerabilities raise significant security…

Computation and Language · Computer Science 2025-10-27 Bushra Sabir , Yansong Gao , Alsharif Abuadbba , M. Ali Babar

Retrieval-Augmented Generation (RAG) has proven effective in mitigating hallucinations in large language models by incorporating external knowledge during inference. However, this integration introduces new security vulnerabilities,…

Cryptography and Security · Computer Science 2025-05-27 Baolei Zhang , Haoran Xin , Jiatong Li , Dongzhe Zhang , Minghong Fang , Zhuqing Liu , Lihai Nie , Zheli Liu

Retrieval-Augmented Generation (RAG) systems, widely used to improve the factual grounding of large language models (LLMs), are increasingly vulnerable to poisoning attacks, where adversaries inject manipulated content into the retriever's…

Information Retrieval · Computer Science 2025-06-04 Liuji Chen , Xiaofang Yang , Yuanzhuo Lu , Jinghao Zhang , Xin Sun , Qiang Liu , Shu Wu , Jing Dong , Liang Wang

Machine-Generated Text (MGT) is becoming increasingly difficult to distinguish from Human-Written Text (HWT). This trend has exacerbated malicious activities such as fake news and online fraud. The generalization ability of fine-tuned…

Computation and Language · Computer Science 2026-05-29 Anyang Song , Ying Cheng , Yiqian Xu , Rui Feng

Retrieval-Augmented Generation (RAG) has been empirically shown to enhance the performance of large language models (LLMs) in knowledge-intensive domains such as healthcare, finance, and legal contexts. Given a query, RAG retrieves relevant…

Cryptography and Security · Computer Science 2025-06-02 Xun Xian , Ganghua Wang , Xuan Bi , Jayanth Srinivasa , Ashish Kundu , Charles Fleming , Mingyi Hong , Jie Ding

Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…

Cryptography and Security · Computer Science 2026-05-28 Jiachen Qian

Large language models (LLMs) are proven to benefit a lot from retrieval-augmented generation (RAG) in alleviating hallucinations confronted with knowledge-intensive questions. RAG adopts information retrieval techniques to inject external…

Computation and Language · Computer Science 2024-10-10 Junda Zhu , Lingyong Yan , Haibo Shi , Dawei Yin , Lei Sha

In recent years, text generation tools utilizing Artificial Intelligence (AI) have occasionally been misused across various domains, such as generating student reports or creative writings. This issue prompts plagiarism detection services…

Computation and Language · Computer Science 2025-04-14 Ahmed K. Kadhim , Lei Jiao , Rishad Shafik , Ole-Christoffer Granmo

Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to knowledge poisoning attacks. Existing attack methods like PoisonedRAG remain detectable due to…

Cryptography and Security · Computer Science 2026-04-10 Ziye Wang , Guanyu Wang , Kailong Wang

Dialogue systems are usually built on either generation-based or retrieval-based approaches, yet they do not benefit from the advantages of different models. In this paper, we propose a Retrieval-Enhanced Adversarial Training (REAT) method…

Computation and Language · Computer Science 2019-05-24 Qingfu Zhu , Lei Cui , Weinan Zhang , Furu Wei , Ting Liu
‹ Prev 1 2 3 10 Next ›