English
Related papers

Related papers: GREAT: Generalizable Backdoor Attacks in RLHF via …

200 papers

Backdoor vulnerabilities widely exist in the fine-tuning of large language models(LLMs). Most backdoor poisoning methods operate mainly at the token level and lack deeper semantic manipulation, which limits stealthiness. In addition, Prior…

Computation and Language · Computer Science 2026-05-13 Ziyu Liu , Tao Li , Tianjie Ni , Xiaolong Lan , Wengang Ma , Tao Yang , Guohua Wang , Junjiang He

Backdoor attacks, representing an emerging threat to the integrity of deep neural networks, have garnered significant attention due to their ability to compromise deep learning systems clandestinely. While numerous backdoor attacks occur…

Cryptography and Security · Computer Science 2024-03-18 Sze Jue Yang , Chinh D. La , Quang H. Nguyen , Kok-Seng Wong , Anh Tuan Tran , Chee Seng Chan , Khoa D. Doan

Reinforcement Learning from Human Feedback (RLHF) is used to align large language models to produce helpful and harmless responses. Yet, prior work showed these models can be jailbroken by finding adversarial prompts that revert the model…

Artificial Intelligence · Computer Science 2024-04-30 Javier Rando , Florian Tramèr

Textual backdoor attacks pose a practical threat to existing systems, as they can compromise the model by inserting imperceptible triggers into inputs and manipulating labels in the training dataset. With cutting-edge generative models such…

Cryptography and Security · Computer Science 2023-05-01 Jiazhao Li , Yijin Yang , Zhuofeng Wu , V. G. Vinod Vydiswaran , Chaowei Xiao

Large Language Models (LLMs) are known to be vulnerable to backdoor attacks, where triggers embedded in poisoned samples can maliciously alter LLMs' behaviors. In this paper, we move beyond attacking LLMs and instead examine backdoor…

Cryptography and Security · Computer Science 2025-02-18 Huaizhi Ge , Yiming Li , Qifan Wang , Yongfeng Zhang , Ruixiang Tang

Backdoor attacks have emerged as one of the major security threats to deep learning models as they can easily control the model's test-time predictions by pre-injecting a backdoor trigger into the model at training time. While backdoor…

Machine Learning · Computer Science 2023-02-07 Yujing Jiang , Xingjun Ma , Sarah Monazam Erfani , James Bailey

Pre-trained general-purpose language models have been a dominating component in enabling real-world natural language processing (NLP) applications. However, a pre-trained model with backdoor can be a severe threat to the applications. Most…

Computation and Language · Computer Science 2021-11-02 Lujia Shen , Shouling Ji , Xuhong Zhang , Jinfeng Li , Jing Chen , Jie Shi , Chengfang Fang , Jianwei Yin , Ting Wang

Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs), by anchoring, adapting, and personalizing their responses to the most relevant knowledge sources. It is particularly useful in chatbot…

Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly operate at the token level, where an injected trigger causes…

Cryptography and Security · Computer Science 2026-04-17 Vu Tuan Truong , Long Bao Le

Backdoor attacks pose severe security threats to large language models (LLMs), where a model behaves normally under benign inputs but produces malicious outputs when a hidden trigger appears. Existing backdoor removal methods typically…

Cryptography and Security · Computer Science 2026-03-17 Jianwei Li , Jung-Eun Kim

Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed trigger setting (e.g., unusual words) may be easily detected by…

Computation and Language · Computer Science 2025-01-09 Jiaming He , Wenbo Jiang , Guanyu Hou , Wenshu Fan , Rui Zhang , Hongwei Li

Prompt-based learning has been widely applied in many low-resource NLP tasks such as few-shot scenarios. However, this paradigm has been shown to be vulnerable to backdoor attacks. Most of the existing attack methods focus on inserting…

Computation and Language · Computer Science 2023-11-30 Zihao Tan , Qingliang Chen , Yongjian Huang , Chen Liang

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Computation and Language · Computer Science 2025-10-07 Jiawei Kong , Hao Fang , Xiaochen Yang , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu , Han Qiu

Despite significant advancements, large language models (LLMs) still struggle with providing accurate answers when lacking domain-specific or up-to-date knowledge. Retrieval-Augmented Generation (RAG) addresses this limitation by…

Cryptography and Security · Computer Science 2025-04-01 Yuefeng Peng , Junda Wang , Hong Yu , Amir Houmansadr

Large Language Models (LLMs) are widely deployed in diverse real-world settings, yet remain vulnerable to jailbreaking, where prompt-based attacks bypass safety filters. We present THREAT (Targeted Harmful generation via Reframing and…

Cryptography and Security · Computer Science 2026-05-22 Shahnewaz Karim Sakib , Swati Kar , Anindya Bijoy Das

Poisoning-based backdoor attacks expose vulnerabilities in the data preparation stage of deep neural network (DNN) training. The DNNs trained on the poisoned dataset will be embedded with a backdoor, making them behave well on clean data…

Computer Vision and Pattern Recognition · Computer Science 2024-05-10 Binxiao Huang , Jason Chun Lok , Chang Liu , Ngai Wong

In recent years, neural backdoor attack has been considered to be a potential security threat to deep learning systems. Such systems, while achieving the state-of-the-art performance on clean data, perform abnormally on inputs with…

Cryptography and Security · Computer Science 2020-10-19 Anh Nguyen , Anh Tran

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…

Computation and Language · Computer Science 2025-08-29 Chen Chen , Yuchen Sun , Jiaxin Gao , Xueluan Gong , Qian Wang , Ziyao Wang , Yongsen Zheng , Kwok-Yan Lam

Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Existing safety training methods largely fail to address this…

Cryptography and Security · Computer Science 2025-10-08 Guangyu Shen , Siyuan Cheng , Xiangzhe Xu , Yuan Zhou , Hanxi Guo , Zhuo Zhang , Xiangyu Zhang

Backdoor attacks significantly compromise the security of large language models by triggering them to output specific and controlled content. Currently, triggers for textual backdoor attacks fall into two categories: fixed-token triggers…

Cryptography and Security · Computer Science 2025-04-01 Jingyi Zheng , Tianyi Hu , Tianshuo Cong , Xinlei He
‹ Prev 1 2 3 10 Next ›