English
Related papers

Related papers: Beyond Explicit Refusals: Soft-Failure Attacks on …

200 papers

Retrieval-augmented generation (RAG) has shown promising potential to enhance the accuracy and factuality of language models (LMs). However, imperfect retrievers or noisy corpora can introduce misleading or even erroneous information to the…

Computation and Language · Computer Science 2025-03-04 Zhepei Wei , Wei-Lin Chen , Yu Meng

Recently, semantic communication (SC) has garnered increasing attention for its efficiency, yet it remains vulnerable to semantic jamming attacks. These attacks entail introducing crafted perturbation signals to legitimate signals over the…

Signal Processing · Electrical Eng. & Systems 2025-01-03 Kequan Zhou , Guangyi Zhang , Yunlong Cai , Qiyu Hu , Guanding Yu

Neural ranking models (NRMs) have shown remarkable success in recent years, especially with pre-trained language models. However, deep neural models are notorious for their vulnerability to adversarial examples. Adversarial attacks may…

Information Retrieval · Computer Science 2022-06-09 Chen Wu , Ruqing Zhang , Jiafeng Guo , Maarten de Rijke , Yixing Fan , Xueqi Cheng

Robust content moderation requires classification systems that can quickly adapt to evolving policies without costly retraining. We present classification using Retrieval-Augmented Generation (RAG), which shifts traditional classification…

Computation and Language · Computer Science 2025-08-11 Richard Willats , Josh Pennington , Aravind Mohan , Bertie Vidgen

Large Language Models (LLMs) enhanced with Retrieval-Augmented Generation (RAG) have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security…

Cryptography and Security · Computer Science 2026-04-10 Zhiyuan Chang , Mingyang Li , Xiaojun Jia , Junjie Wang , Yuekai Huang , Ziyou Jiang , Yang Liu , Qing Wang

Retrieval-augmented Generation (RAG) is a prevalent approach for domain-specific LLMs, yet it is often plagued by "Retrieval Hallucinations"--a phenomenon where fine-tuned models fail to recognize and act upon poor-quality retrieved…

Artificial Intelligence · Computer Science 2026-01-21 Letian Zhang , Guanghao Meng , Xudong Ren , Yiming Wang , Shu-Tao Xia

Retrieval-Augmented Generation (RAG) has been an effective approach to mitigate hallucinations in large language models (LLMs) by incorporating up-to-date and domain-specific knowledge. Recently, there has been a trend of storing up-to-date…

Cryptography and Security · Computer Science 2025-02-11 Mingrui Liu , Sixiao Zhang , Cheng Long

Adversarial examples are inputs intentionally generated for fooling a deep neural network. Recent studies have proposed unrestricted adversarial attacks that are not norm-constrained. However, the previous unrestricted attack methods still…

Computer Vision and Pattern Recognition · Computer Science 2022-08-25 Dongbin Na , Sangwoo Ji , Jong Kim

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

Diffusion Language Models (DLMs) have recently demonstrated remarkable capabilities in natural language processing tasks. However, the potential of Retrieval-Augmented Generation (RAG), which shows great successes for enhancing large…

Machine Learning · Computer Science 2026-01-19 Chuanyue Yu , Jiahui Wang , Yuhan Li , Heng Chang , Ge Lan , Qingyun Sun , Jia Li , Jianxin Li , Ziwei Zhang

The use of large language models (LLMs) in peer review systems has attracted growing attention, making it essential to examine their potential vulnerabilities. Prior attacks rely on prompt injection, which alters manuscript content and…

Computation and Language · Computer Science 2026-01-13 Masahiro Kaneko

Retrieval-Augmented Generation RAG systems enhance large language models by grounding responses in external knowledge bases, but conventional RAG architectures operate with static corpora that cannot evolve from user interactions. We…

Artificial Intelligence · Computer Science 2025-12-30 Teja Chinthala

Presently, with the assistance of advanced LLM application development frameworks, more and more LLM-powered applications can effortlessly augment the LLMs' knowledge with external content using the retrieval augmented generation (RAG)…

Cryptography and Security · Computer Science 2024-04-29 Quan Zhang , Binqi Zeng , Chijin Zhou , Gwihwan Go , Heyuan Shi , Yu Jiang

AI-generated text (AIGT) detection evasion aims to reduce the detection probability of AIGT, helping to identify weaknesses in detectors and enhance their effectiveness and reliability in practical applications. Although existing evasion…

Cryptography and Security · Computer Science 2025-08-25 Yinghan Zhou , Juan Wen , Wanli Peng , Zhengxian Wu , Ziwei Zhang , Yiming Xue

Large language models (LLMs) excel in various tasks but remain vulnerable to jailbreak attacks, where adversaries manipulate prompts to generate harmful outputs. Examining jailbreak prompts helps uncover the shortcomings of LLMs. However,…

Computation and Language · Computer Science 2024-12-18 Weixiong Zheng , Peijian Zeng , Yiwei Li , Hongyan Wu , Nankai Lin , Junhao Chen , Aimin Yang , Yongmei Zhou

Retrieval-Augmented Generation (RAG) increases the reliability and trustworthiness of the LLM response and reduces hallucination by eliminating the need for model retraining. It does so by adding external data into the LLM's context. We…

Cryptography and Security · Computer Science 2026-05-25 Aritra Dhar , Vasilije Stambolic , Lukas Cavigelli

Recent studies on adversarial examples expose vulnerabilities of natural language processing (NLP) models. Existing techniques for generating adversarial examples are typically driven by deterministic hierarchical rules that are agnostic to…

Cryptography and Security · Computer Science 2024-03-25 Mingze Ni , Zhensu Sun , Wei Liu

Retrieval-augmented generation (RAG) has become central to large language model (LLM) deployments, grounding responses in enterprise or proprietary data to reduce hallucinations. However, this design introduces a new privacy risk: model…

Cryptography and Security · Computer Science 2026-05-26 Nguyen Linh Bao Nguyen , Wanlun Ma , Viet Vo , Alsharif Abuadbba , Minghong Fang , Jun Zhang , Yang Xiang

Large language models (LLMs) have raised concerns about potential security threats despite performing significantly in Natural Language Processing (NLP). Backdoor attacks initially verified that LLM is doing substantial harm at all stages,…

Cryptography and Security · Computer Science 2024-07-09 Pengzhou Cheng , Yidong Ding , Tianjie Ju , Zongru Wu , Wei Du , Ping Yi , Zhuosheng Zhang , Gongshen Liu

In sensitive domains, Retrieval-Augmented Generation (RAG) must be interpretable and robust because errors do not just mislead, they invite lawsuits, undermine scholarly credibility, and breach compliance. Stakeholders require traceable…

Computation and Language · Computer Science 2026-01-21 Yash Saxena , Ankur Padia , Mandar S Chaudhary , Kalpa Gunaratna , Srinivasan Parthasarathy , Manas Gaur