English
Related papers

Related papers: Defending Against Disinformation Attacks in Open-D…

200 papers

The proliferation of online misinformation has posed significant threats to public interest. While numerous online users actively participate in the combat against misinformation, many of such responses can be characterized by the lack of…

Computation and Language · Computer Science 2024-03-25 Zhenrui Yue , Huimin Zeng , Yimeng Lu , Lanyu Shang , Yang Zhang , Dong Wang

Retrieval-augmented generation (RAG) enhances large language model (LLM) reasoning by retrieving external documents, but also opens up new attack surfaces. We study knowledge-base poisoning attacks in RAG, where an attacker injects…

Information Retrieval · Computer Science 2026-04-15 Hongru Song , Yu-An Liu , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng

Large Language Models (LLMs) are constrained by outdated information and a tendency to generate incorrect data, commonly referred to as "hallucinations." Retrieval-Augmented Generation (RAG) addresses these limitations by combining the…

Cryptography and Security · Computer Science 2024-06-07 Jiaqi Xue , Mengxin Zheng , Yebowen Hu , Fei Liu , Xun Chen , Qian Lou

Adversarial attacks can mislead neural network classifiers. The defense against adversarial attacks is important for AI safety. Adversarial purification is a family of approaches that defend adversarial attacks with suitable pre-processing.…

Machine Learning · Computer Science 2023-10-31 Boya Zhang , Weijian Luo , Zhihua Zhang

Retrieval-Augmented Generation (RAG) systems enhance response credibility and traceability by displaying reference contexts, but this transparency simultaneously introduces a novel black-box attack vector. Existing document poisoning…

Computation and Language · Computer Science 2026-01-27 Runqi Sui

Retrieval-Augmented Generation (RAG) systems are vulnerable to knowledge base poisoning, yet existing attacks have been evaluated almost exclusively against vanilla retrieve-then-generate pipelines. Architectures designed to handle…

Cryptography and Security · Computer Science 2026-05-08 Samuel Korn

The raise of machine learning and deep learning led to significant improvement in several domains. This change is supported by both the dramatic rise in computation power and the collection of large datasets. Such massive datasets often…

Machine Learning · Computer Science 2022-11-24 Hamid Jalalzai , Elie Kadoche , Rémi Leluc , Vincent Plassier

With the rise of third parties in the machine learning pipeline, the service provider in "Machine Learning as a Service" (MLaaS), or external data contributors in online learning, or the retraining of existing models, the need to ensure the…

Cryptography and Security · Computer Science 2021-05-20 Jialin Wen , Benjamin Zi Hao Zhao , Minhui Xue , Alina Oprea , Haifeng Qian

Retrieval-Augmented Generation (RAG) depends on document ranking to provide useful evidence for generation, but conventional reranking methods mainly optimize query-document relevance rather than generation usefulness. A relevant document…

Computation and Language · Computer Science 2026-05-07 Zhipeng Song , Yizhi Zhou , Xiangyu Kong , Jiulong Jiao , Xuezhou Ye , Chunqi Gao , Xueqing Shi , Yuhang Zhou , Heng Qi

Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of…

Cryptography and Security · Computer Science 2021-05-11 Jian Chen , Xuxin Zhang , Rui Zhang , Chen Wang , Ling Liu

The unprecedented availability of training data fueled the rapid development of powerful neural networks in recent years. However, the need for such large amounts of data leads to potential threats such as poisoning attacks: adversarial…

Machine Learning · Computer Science 2024-03-21 Fabio De Gaspari , Dorjan Hitaj , Luigi V. Mancini

We present a certified defense to clean-label poisoning attacks under $\ell_2$-norm. These attacks work by injecting a small number of poisoning samples (e.g., 1%) that contain bounded adversarial perturbations into the training data to…

Cryptography and Security · Computer Science 2025-06-03 Sanghyun Hong , Nicholas Carlini , Alexey Kurakin

Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e.g.,} sentiment prediction), is a serious security concern due to the evasive nature of…

Cryptography and Security · Computer Science 2024-08-23 Jayaram Raghuram , George Kesidis , David J. Miller

A powerful category of (invisible) data poisoning attacks modify a subset of training examples by small adversarial perturbations to change the prediction of certain test-time data. Existing defense mechanisms are not desirable to deploy in…

Cryptography and Security · Computer Science 2023-07-21 Tian Yu Liu , Yu Yang , Baharan Mirzasoleiman

Retrieval-Augmented Generation (RAG) can alleviate hallucinations of Large Language Models (LLMs) by referencing external documents. However, the misinformation in external documents may mislead LLMs' generation. To address this issue, we…

Computation and Language · Computer Science 2024-12-18 Boyi Deng , Wenjie Wang , Fengbin Zhu , Qifan Wang , Fuli Feng

Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense mechanisms have made notable progress, they fail to protect…

Machine Learning · Computer Science 2025-04-29 Georgios Syros , Anshuman Suri , Farinaz Koushanfar , Cristina Nita-Rotaru , Alina Oprea

We show that continual pretraining on plausible misinformation can overwrite specific factual knowledge in large language models without degrading overall performance. Unlike prior poisoning work under static pretraining, we study repeated…

Machine Learning · Computer Science 2026-02-09 Svetlana Churina , Niranjan Chebrolu , Kokil Jaidka

Safety classifiers are critical in mitigating toxicity on online forums such as social media and in chatbots. Still, they continue to be vulnerable to emergent, and often innumerable, adversarial attacks. Traditional automated adversarial…

Computation and Language · Computer Science 2024-06-26 Yash Kumar Lal , Preethi Lahoti , Aradhana Sinha , Yao Qin , Ananth Balashankar

Adversarial purification is a defense mechanism for safeguarding classifiers against adversarial attacks without knowing the type of attacks or training of the classifier. These techniques characterize and eliminate adversarial…

Cryptography and Security · Computer Science 2024-02-13 Raha Moraffah , Shubh Khandelwal , Amrita Bhattacharjee , Huan Liu

An adversarial deep learning approach is presented to launch over-the-air spectrum poisoning attacks. A transmitter applies deep learning on its spectrum sensing results to predict idle time slots for data transmission. In the meantime, an…

Networking and Internet Architecture · Computer Science 2019-11-05 Yalin E. Sagduyu , Yi Shi , Tugba Erpek