English
Related papers

Related papers: TCAP: Tri-Component Attention Profiling for Unsupe…

200 papers

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

Multimodal pretrained models are vulnerable to backdoor attacks, yet most existing methods rely on visual or multimodal triggers, which are impractical since visually embedded triggers rarely occur in real-world data. To overcome this…

Cryptography and Security · Computer Science 2026-04-08 Yiyang Zhang , Chaojian Yu , Ziming Hong , Yuanjie Shao , Qinmu Peng , Tongliang Liu , Xinge You

Institutions with limited data and computing resources often outsource model training to third-party providers in a semi-honest setting, assuming adherence to prescribed training protocols with pre-defined learning paradigm (e.g.,…

Machine Learning · Computer Science 2025-04-02 Xuan Wang , Siyuan Liang , Dongping Liao , Han Fang , Aishan Liu , Xiaochun Cao , Yu-liang Lu , Ee-Chien Chang , Xitong Gao

Instruction tuning enhances large vision-language models (LVLMs) but increases their vulnerability to backdoor attacks due to their open design. Unlike prior studies in static settings, this paper explores backdoor attacks in LVLM…

Computer Vision and Pattern Recognition · Computer Science 2024-12-17 Siyuan Liang , Jiawei Liang , Tianyu Pang , Chao Du , Aishan Liu , Mingli Zhu , Xiaochun Cao , Dacheng Tao

Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model parameter fault injection attacks. Recent studies have shown that bit-flip attacks (BFAs),…

Cryptography and Security · Computer Science 2026-02-23 Jingkai Guo , Chaitali Chakrabarti , Deliang Fan

Despite the advanced capabilities of contemporary machine learning (ML) models, they remain vulnerable to adversarial and backdoor attacks. This vulnerability is particularly concerning in real-world deployments, where compromised models…

Backdoor attacks become a significant security concern for deep neural networks in recent years. An image classification model can be compromised if malicious backdoors are injected into it. This corruption will cause the model to function…

Cryptography and Security · Computer Science 2024-03-13 Hongwei Zhang , Xiaoyin Xu , Dongsheng An , Xianfeng Gu , Min Zhang

Recent studies have shown that deep neural networks (DNNs) are vulnerable to backdoor attacks, where a designed trigger is injected into the dataset, causing erroneous predictions when activated. In this paper, we propose a novel defense…

Machine Learning · Computer Science 2025-08-08 Wenjie Huo , Katinka Wolter

Large pre-trained Vision-Language Models (VLMs) such as CLIP have demonstrated excellent zero-shot generalizability across various downstream tasks. However, recent studies have shown that the inference performance of CLIP can be greatly…

Computer Vision and Pattern Recognition · Computer Science 2024-11-21 Xin Wang , Kai Chen , Jiaming Zhang , Jingjing Chen , Xingjun Ma

Adversaries can embed backdoors in deep learning models by introducing backdoor poison samples into training datasets. In this work, we investigate how to detect such poison samples to mitigate the threat of backdoor attacks. First, we…

Machine Learning · Computer Science 2023-06-21 Xiangyu Qi , Tinghao Xie , Jiachen T. Wang , Tong Wu , Saeed Mahloujifar , Prateek Mittal

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of model safety during fine-tuning, we introduce LookAhead…

Computation and Language · Computer Science 2025-12-22 Kangwei Liu , Mengru Wang , Yujie Luo , Lin Yuan , Mengshu Sun , Lei Liang , Zhiqiang Zhang , Jun Zhou , Bryan Hooi , Shumin Deng

Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Juncheng Li , Yige Li , Hanxun Huang , Yunhao Chen , Xin Wang , Yixu Wang , Xingjun Ma , Yu-Gang Jiang

Transferable backdoors pose a severe threat to the Pre-trained Language Models (PLMs) supply chain, yet defensive research remains nascent, primarily relying on detecting anomalies in the output feature space. We identify a critical flaw…

Cryptography and Security · Computer Science 2025-12-09 Tianhang Zhao , Wei Du , Haodong Zhao , Sufeng Duan , Gongshen Liu

Large vision-language models (LVLMs) have achieved impressive performance across a wide range of vision-language tasks, while they remain vulnerable to backdoor attacks. Existing backdoor attacks on LVLMs aim to force the victim model to…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Zhifang Zhang , Qiqi Tao , Jiaqi Lv , Na Zhao , Lei Feng , Joey Tianyi Zhou

Language Models (LMs) are becoming increasingly popular in real-world applications. Outsourcing model training and data hosting to third-party platforms has become a standard method for reducing costs. In such a situation, the attacker can…

Cryptography and Security · Computer Science 2024-12-05 Pengzhou Cheng , Zongru Wu , Wei Du , Haodong Zhao , Wei Lu , Gongshen Liu

Backdoor attack introduces artificial vulnerabilities into the model by poisoning a subset of the training data via injecting triggers and modifying labels. Various trigger design strategies have been explored to attack text classifiers,…

Computation and Language · Computer Science 2021-09-23 Zichao Li , Dheeraj Mekala , Chengyu Dong , Jingbo Shang

Large language model fine-tuning APIs enable widespread model customization, yet pose significant safety risks. Recent work shows that adversaries can exploit access to these APIs to bypass model safety mechanisms by encoding harmful…

Machine Learning · Computer Science 2025-08-26 Jack Youstra , Mohammed Mahfoud , Yang Yan , Henry Sleight , Ethan Perez , Mrinank Sharma

At present, backdoor attacks attract attention as they do great harm to deep learning models. The adversary poisons the training data making the model being injected with a backdoor after being trained unconsciously by victims using the…

Cryptography and Security · Computer Science 2023-03-06 Shengfang Zhai , Qingni Shen , Xiaoyi Chen , Weilong Wang , Cong Li , Yuejian Fang , Zhonghai Wu

Contrastive language-image pretraining (CLIP) has been found to be vulnerable to poisoning backdoor attacks where the adversary can achieve an almost perfect attack success rate on CLIP models by poisoning only 0.01\% of the training…

Machine Learning · Computer Science 2025-02-11 Hanxun Huang , Sarah Erfani , Yige Li , Xingjun Ma , James Bailey

Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this work, we conduct a pilot study showing that PLMs as few-shot…

Machine Learning · Computer Science 2023-09-26 Zhaohan Xi , Tianyu Du , Changjiang Li , Ren Pang , Shouling Ji , Jinghui Chen , Fenglong Ma , Ting Wang