English
Related papers

Related papers: Inverting Trojans in LLMs

200 papers

With the rapid rise of personalized AI, customized large language models (LLMs) equipped with Chain of Thought (COT) reasoning now power millions of AI agents. However, their complex reasoning processes introduce new and largely unexplored…

Cryptography and Security · Computer Science 2025-11-25 Zhen Guo , Shanghao Shi , Shamim Yazdani , Ning Zhang , Reza Tourani

It has been proved that deep neural networks are facing a new threat called backdoor attacks, where the adversary can inject backdoors into the neural network model through poisoning the training dataset. When the input containing some…

Cryptography and Security · Computer Science 2021-03-16 Chuanshuai Chen , Jiazhu Dai

Adversarial attacks on deep learning-based models pose a significant threat to the current AI infrastructure. Among them, Trojan attacks are the hardest to defend against. In this paper, we first introduce a variation of the Badnet kind of…

Computer Vision and Pattern Recognition · Computer Science 2022-07-11 Haripriya Harikumar , Santu Rana , Kien Do , Sunil Gupta , Wei Zong , Willy Susilo , Svetha Venkastesh

Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…

Cryptography and Security · Computer Science 2026-05-18 Jiate Li , Defu Cao , Li Li , Wei Yang , Yuehan Qin , Chenxiao Yu , Tiannuo Yang , Ryan A. Rossi , Yan Liu , Xiyang Hu , Yue Zhao

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

Recent studies have shown that Large Language Models (LLMs) are vulnerable to data poisoning attacks, where malicious training examples embed hidden behaviours triggered by specific input patterns. However, most existing works assume a…

Computation and Language · Computer Science 2025-10-10 Sanhanat Sivapiromrat , Caiqi Zhang , Marco Basaldella , Nigel Collier

The remarkable performance of large language models (LLMs) in generation tasks has enabled practitioners to leverage publicly available models to power custom applications, such as chatbots and virtual assistants. However, the data used to…

Artificial Intelligence · Computer Science 2025-03-28 Yuetai Li , Zhangchen Xu , Fengqing Jiang , Luyao Niu , Dinuka Sahabandu , Bhaskar Ramasubramanian , Radha Poovendran

Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generate incorrect outputs in the presence of specific, often…

Machine Learning · Computer Science 2025-03-25 Sharon Lin , Krishnamurthy , Dvijotham , Jamie Hayes , Chongyang Shi , Ilia Shumailov , Shuang Song

Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks. This impedes their wider adoption, especially in mission critical applications. This paper tackles the problem of Trojan…

Computer Vision and Pattern Recognition · Computer Science 2022-04-05 Xiaoling Hu , Xiao Lin , Michael Cogswell , Yi Yao , Susmit Jha , Chao Chen

Textual backdoor attacks present a substantial security risk to Large Language Models (LLM). It embeds carefully chosen triggers into a victim model at the training stage, and makes the model erroneously predict inputs containing the same…

Computation and Language · Computer Science 2024-07-08 Xinglin Li , Xianwen He , Yao Li , Minhao Cheng

Machine learning backdoors have the property that the machine learning model should work as expected on normal inputs, but when the input contains a specific $\textit{trigger}$, it behaves as the attacker desires. Detecting such triggers…

Cryptography and Security · Computer Science 2026-03-12 Eirik Høyheim , Magnus Wiik Eckhoff , Gudmund Grov , Robert Flood , David Aspinall

Backdoor attacks pose a critical threat by embedding hidden triggers into inputs, causing models to misclassify them into target labels. While extensive research has focused on mitigating these attacks in object recognition models through…

Computer Vision and Pattern Recognition · Computer Science 2025-04-09 Kyle Stein , Andrew Arash Mahyari , Guillermo Francia , Eman El-Sheikh

Inference optimization is a vital technique for deploying LLMs at scale. Compilation is the most widely adopted optimization technique for LLMs. While it assumes semantic equivalence between the original and compiled graphs, we first…

Cryptography and Security · Computer Science 2026-05-21 Yifei Wang , Tianlin Li , Xiaohan Zhang , Yida Yang , Xiaoyu Zhang , Li Pan

Multimodal Large Language Models (MLLMs) have achieved remarkable success in cross-modal understanding and generation, yet their deployment is threatened by critical safety vulnerabilities. While prior works have demonstrated the…

Cryptography and Security · Computer Science 2026-04-22 Kun Wang , Cheng Qian , Miao Yu , Lilan Peng , Liang Lin , Jiaming Zhang , Tianyu Zhang , Yu Cheng , Yang Wang

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

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

Cryptography and Security · Computer Science 2026-04-15 Haotian Jin , Yang Li , Haihui Fan , Lin Shen , Xiangfang Li , Bo Li

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Cryptography and Security · Computer Science 2025-11-24 Yige Li , Zhe Li , Wei Zhao , Nay Myat Min , Hanxun Huang , Xingjun Ma , Jun Sun

Machine learning (ML) models that use deep neural networks are vulnerable to backdoor attacks. Such attacks involve the insertion of a (hidden) trigger by an adversary. As a consequence, any input that contains the trigger will cause the…

Cryptography and Security · Computer Science 2022-03-30 Arezoo Rajabi , Bhaskar Ramasubramanian , Radha Poovendran

Insertion of hardware Trojans (HTs) in integrated circuits is a pernicious threat. Since HTs are activated under rare trigger conditions, detecting them using random logic simulations is infeasible. In this work, we design a reinforcement…

Machine Learning · Computer Science 2022-08-30 Vasudev Gohil , Satwik Patnaik , Hao Guo , Dileep Kalathil , Jeyavijayan , Rajendran

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

Computation and Language · Computer Science 2024-11-28 Chen Chen , Yuchen Sun , Xueluan Gong , Jiaxin Gao , Kwok-Yan Lam