English
Related papers

Related papers: Unveiling and Mitigating Backdoor Vulnerabilities …

200 papers

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…

Cryptography and Security · Computer Science 2025-09-23 Brendan Murphy , Dillon Bowen , Shahrad Mohammadzadeh , Tom Tseng , Julius Broomfield , Adam Gleave , Kellin Pelrine

Backdoor attack is a powerful attack algorithm to deep learning model. Recently, GNN's vulnerability to backdoor attack has been proved especially on graph classification task. In this paper, we propose the first backdoor detection and…

Artificial Intelligence · Computer Science 2022-09-08 Bingchen Jiang , Zhao Li

Convolutional neural networks (CNNs), one of the key architectures of deep learning models, have achieved superior performance on many machine learning tasks such as image classification, video recognition, and power systems. Despite their…

Machine Learning · Computer Science 2024-07-17 Hanxiao Lu , Zeyu Huang , Ren Wang

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the…

Cryptography and Security · Computer Science 2020-09-16 Haoliang Li , Yufei Wang , Xiaofei Xie , Yang Liu , Shiqi Wang , Renjie Wan , Lap-Pui Chau , Alex C. Kot

DNNs' demand for massive data forces practitioners to collect data from the Internet without careful check due to the unacceptable cost, which brings potential risks of backdoor attacks. A backdoored model always predicts a target class in…

Machine Learning · Computer Science 2022-02-23 Yinghua Gao , Dongxian Wu , Jingfeng Zhang , Guanhao Gan , Shu-Tao Xia , Gang Niu , Masashi Sugiyama

Parameter-efficient fine-tuning (PEFT) can bridge the gap between large language models (LLMs) and downstream tasks. However, PEFT has been proven vulnerable to malicious attacks. Research indicates that poisoned LLMs, even after PEFT,…

Computation and Language · Computer Science 2025-05-21 Shuai Zhao , Xiaobao Wu , Cong-Duy Nguyen , Yanhao Jia , Meihuizi Jia , Yichao Feng , Luu Anh Tuan

Adversarial machine learning has exposed several security hazards of neural models and has become an important research topic in recent times. Thus far, the concept of an "adversarial perturbation" has exclusively been used with reference…

Machine Learning · Computer Science 2020-09-22 Siddhant Garg , Adarsh Kumar , Vibhor Goel , Yingyu Liang

Deep neural network (DNN) classifiers are vulnerable to backdoor attacks. An adversary poisons some of the training data in such attacks by installing a trigger. The goal is to make the trained DNN output the attacker's desired class…

Machine Learning · Computer Science 2022-10-14 Hadi M. Dolatabadi , Sarah Erfani , Christopher Leckie

Deep neural networks have been shown to be vulnerable to backdoor, or trojan, attacks where an adversary has embedded a trigger in the network at training time such that the model correctly classifies all standard inputs, but generates a…

Machine Learning · Computer Science 2021-09-08 Greg Fields , Mohammad Samragh , Mojan Javaheripi , Farinaz Koushanfar , Tara Javidi

Since Deep Learning (DL) backdoor attacks have been revealed as one of the most insidious adversarial attacks, a number of countermeasures have been developed with certain assumptions defined in their respective threat models. However, the…

Cryptography and Security · Computer Science 2022-04-14 Huming Qiu , Hua Ma , Zhi Zhang , Alsharif Abuadbba , Wei Kang , Anmin Fu , Yansong Gao

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

Machine learning systems are vulnerable to backdoor attacks, where attackers manipulate model behavior through data tampering or architectural modifications. Traditional backdoor attacks involve injecting malicious samples with specific…

Cryptography and Security · Computer Science 2025-09-24 Yuan Ma , Jiankang Wei , Yilun Lyu , Kehao Chen , Jingtong Huang

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model checkpoints on the web poses considerable risks, including the…

Cryptography and Security · Computer Science 2024-04-02 Yuxin Wen , Leo Marchyok , Sanghyun Hong , Jonas Geiping , Tom Goldstein , Nicholas Carlini

As machine learning (ML) systems are being increasingly employed in the real world to handle sensitive tasks and make decisions in various fields, the security and privacy of those models have also become increasingly critical. In…

Cryptography and Security · Computer Science 2023-02-21 Marwan Omar

Pruning-based unlearning has recently emerged as a fast, training-free, and data-independent approach to remove undesired concepts from diffusion models. It promises high efficiency and robustness, offering an attractive alternative to…

Computer Vision and Pattern Recognition · Computer Science 2026-03-10 Ci Zhang , Zhaojun Ding , Chence Yang , Jun Liu , Xiaoming Zhai , Shaoyi Huang , Beiwen Li , Xiaolong Ma , Jin Lu , Geng Yuan

Malicious clients can attack federated learning systems using malicious data, including backdoor samples, during the training phase. The compromised global model will perform well on the validation dataset designed for the task, but a small…

Cryptography and Security · Computer Science 2021-01-18 Chen Wu , Xian Yang , Sencun Zhu , Prasenjit Mitra

Backdoor attacks inject poisoning samples during training, with the goal of forcing a machine learning model to output an attacker-chosen class when presented a specific trigger at test time. Although backdoor attacks have been demonstrated…

This paper proposes a new defense against neural network backdooring attacks that are maliciously trained to mispredict in the presence of attacker-chosen triggers. Our defense is based on the intuition that the feature extraction layers of…

Machine Learning · Computer Science 2023-02-24 Hao Fu , Akshaj Kumar Veldanda , Prashanth Krishnamurthy , Siddharth Garg , Farshad Khorrami

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

Deep neural networks are susceptible to backdoor attacks, where adversaries manipulate model predictions by inserting malicious samples into the training data. Currently, there is still a significant challenge in identifying suspicious…

Machine Learning · Computer Science 2025-04-17 Wei Li , Pin-Yu Chen , Sijia Liu , Ren Wang