English
Related papers

Related papers: SynGhost: Invisible and Universal Task-agnostic Ba…

200 papers

Neural code models have been increasingly incorporated into software development processes. However, their susceptibility to backdoor attacks presents a significant security risk. The state-of-the-art understanding focuses on…

Software Engineering · Computer Science 2025-12-23 Junyao Ye , Zhen Li , Xi Tang , Shouhuai Xu , Deqing Zou , Zhongsheng Yuan

Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…

Cryptography and Security · Computer Science 2025-03-07 Haiyang Yu , Tian Xie , Jiaping Gui , Pengyang Wang , Ping Yi , Yue Wu

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

Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…

Computer Vision and Pattern Recognition · Computer Science 2025-06-10 Zhiyuan Zhong , Zhen Sun , Yepang Liu , Xinlei He , Guanhong Tao

Backdoor attacks for neural code models have gained considerable attention due to the advancement of code intelligence. However, most existing works insert triggers into task-specific data for code-related downstream tasks, thereby limiting…

Cryptography and Security · Computer Science 2023-06-16 Yanzhou Li , Shangqing Liu , Kangjie Chen , Xiaofei Xie , Tianwei Zhang , Yang Liu

Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patches or visible noise, which are vulnerable to human…

Computer Vision and Pattern Recognition · Computer Science 2025-04-04 Hanrong Zhang , Zhenting Wang , Boheng Li , Fulin Lin , Tingxu Han , Mingyu Jin , Chenlu Zhan , Mengnan Du , Hongwei Wang , Shiqing Ma

Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word embedding vectors. Such attacks can be easily affected by…

Computation and Language · Computer Science 2023-05-30 Kai Mei , Zheng Li , Zhenting Wang , Yang Zhang , Shiqing Ma

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Computation and Language · Computer Science 2026-05-14 Liang Lin , Miao Yu , Moayad Aloqaily , Zhenhong Zhou , Kun Wang , Linsey Pang , Prakhar Mehrotra , Qingsong Wen

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

Semantic Communication (SC) backdoor attacks aim to utilize triggers to manipulate the system into producing predetermined outputs via backdoored shared knowledge. Current SC backdoors adopt monomorphic paradigms with single attack target,…

Cryptography and Security · Computer Science 2026-04-28 Xiao Yang , Yuni Lai , Gaolei Li , Jun Wu , Kai Zhou , Jianhua Li , Mingzhe Chen

Textual backdoor attacks pose significant security threats. Current detection approaches, typically relying on intermediate feature representation or reconstructing potential triggers, are task-specific and less effective beyond sentence…

Computation and Language · Computer Science 2024-03-27 Weimin Lyu , Xiao Lin , Songzhu Zheng , Lu Pang , Haibin Ling , Susmit Jha , Chao Chen

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Machine Learning · Computer Science 2025-10-21 Bingqi Shang , Yiwei Chen , Yihua Zhang , Bingquan Shen , Sijia Liu

Backdoor attacks are commonly executed by contaminating training data, such that a trigger can activate predetermined harmful effects during the test phase. In this work, we present AnyDoor, a test-time backdoor attack against multimodal…

Computation and Language · Computer Science 2024-02-14 Dong Lu , Tianyu Pang , Chao Du , Qian Liu , Xianjun Yang , Min Lin

Generative large language models (LLMs) have achieved state-of-the-art results on a wide range of tasks, yet they remain susceptible to backdoor attacks: carefully crafted triggers in the input can manipulate the model to produce…

Artificial Intelligence · Computer Science 2025-05-20 Yige Li , Hanxun Huang , Yunhan Zhao , Xingjun Ma , Jun Sun

With the broad application of deep neural networks (DNNs), backdoor attacks have gradually attracted attention. Backdoor attacks are insidious, and poisoned models perform well on benign samples and are only triggered when given specific…

Machine Learning · Computer Science 2022-07-12 Chang Yue , Peizhuo Lv , Ruigang Liang , Kai Chen

Graph Prompt Learning (GPL) bridges significant disparities between pretraining and downstream applications to alleviate the knowledge transfer bottleneck in real-world graph learning. While GPL offers superior effectiveness in graph…

Machine Learning · Computer Science 2024-05-29 Xiaoting Lyu , Yufei Han , Wei Wang , Hangwei Qian , Ivor Tsang , Xiangliang Zhang

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Cryptography and Security · Computer Science 2026-02-17 Anudeep Das , Prach Chantasantitam , Gurjot Singh , Lipeng He , Mariia Ponomarenko , Florian Kerschbaum

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs…

Computation and Language · Computer Science 2025-05-26 Pengzhou Cheng , Haowen Hu , Zheng Wu , Zongru Wu , Tianjie Ju , Zhuosheng Zhang , Gongshen Liu

Neural backdoors represent insidious cybersecurity loopholes that render learning machinery vulnerable to unauthorised manipulations, potentially enabling the weaponisation of artificial intelligence with catastrophic consequences. A…

Cryptography and Security · Computer Science 2026-05-01 Ching-Chun Chang , Kai Gao , Shuying Xu , Anastasia Kordoni , Christopher Leckie , Isao Echizen

We investigate security concerns of the emergent instruction tuning paradigm, that models are trained on crowdsourced datasets with task instructions to achieve superior performance. Our studies demonstrate that an attacker can inject…

Computation and Language · Computer Science 2024-04-04 Jiashu Xu , Mingyu Derek Ma , Fei Wang , Chaowei Xiao , Muhao Chen