English
Related papers

Related papers: GradSentry: Gradient Spectral Entropy for Backdoor…

200 papers

Despite the notable success of language models (LMs) in various natural language processing (NLP) tasks, the reliability of LMs is susceptible to backdoor attacks. Prior research attempts to mitigate backdoor learning while training the LMs…

Computation and Language · Computer Science 2024-06-04 Zongru Wu , Zhuosheng Zhang , Pengzhou Cheng , Gongshen Liu

Backdoor attacks have emerged as a prominent threat to natural language processing (NLP) models, where the presence of specific triggers in the input can lead poisoned models to misclassify these inputs to predetermined target classes.…

Cryptography and Security · Computer Science 2023-10-30 Lu Yan , Zhuo Zhang , Guanhong Tao , Kaiyuan Zhang , Xuan Chen , Guangyu Shen , Xiangyu Zhang

Deep learning models have been shown to be vulnerable to adversarial attacks. In particular, gradient-based attacks have demonstrated high success rates recently. The gradient measures how each image pixel affects the model output, which…

Computer Vision and Pattern Recognition · Computer Science 2022-02-03 Hanbin Hong , Yuan Hong , Yu Kong

Deep Learning backdoor attacks have a threat model similar to traditional cyber attacks. Attack forensics, a critical counter-measure for traditional cyber attacks, is hence of importance for defending model backdoor attacks. In this paper,…

Cryptography and Security · Computer Science 2023-01-18 Siyuan Cheng , Guanhong Tao , Yingqi Liu , Shengwei An , Xiangzhe Xu , Shiwei Feng , Guangyu Shen , Kaiyuan Zhang , Qiuling Xu , Shiqing Ma , Xiangyu Zhang

Large Language Models (LLMs) have demonstrated remarkable capabilities, yet their deployment is frequently undermined by undesirable behaviors such as generating harmful content, factual inaccuracies, and societal biases. Diagnosing the…

Computation and Language · Computer Science 2025-10-06 Zhe Li , Wei Zhao , Yige Li , Jun Sun

Deep learning models have consistently outperformed traditional machine learning models in various classification tasks, including image classification. As such, they have become increasingly prevalent in many real world applications…

Cryptography and Security · Computer Science 2018-08-31 Cong Liao , Haoti Zhong , Anna Squicciarini , Sencun Zhu , David Miller

Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively implant a backdoor, multiple \textbf{triggers} are proposed for…

Cryptography and Security · Computer Science 2025-10-08 Zhixiao Wu , Yao Lu , Jie Wen , Hao Sun , Qi Zhou , Guangming Lu

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

Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…

Cryptography and Security · Computer Science 2026-04-28 Wei Guo , Maura Pintor , Ambra Demontis , Battista Biggio

Deep neural networks (DNNs) and natural language processing (NLP) systems have developed rapidly and have been widely used in various real-world fields. However, they have been shown to be vulnerable to backdoor attacks. Specifically, the…

Computation and Language · Computer Science 2023-01-26 Jiali Wei , Ming Fan , Wenjing Jiao , Wuxia Jin , Ting Liu

Predicitions made by neural networks can be fraudulently altered by so-called poisoning attacks. A special case are backdoor poisoning attacks. We study suitable detection methods and introduce a new method called Heatmap Clustering. There,…

Machine Learning · Computer Science 2022-04-28 Lukas Schulth , Christian Berghoff , Matthias Neu

Training deep neural networks (DNNs) usually requires massive training data and computational resources. Users who cannot afford this may prefer to outsource training to a third party or resort to publicly available pre-trained models.…

Cryptography and Security · Computer Science 2023-02-27 Najeeb Moharram Jebreel , Josep Domingo-Ferrer , Yiming Li

Federated learning collaboratively trains a neural network on a global server, where each local client receives the current global model weights and sends back parameter updates (gradients) based on its local private data. The process of…

Machine Learning · Computer Science 2025-01-28 Kaiyuan Zhang , Siyuan Cheng , Guangyu Shen , Bruno Ribeiro , Shengwei An , Pin-Yu Chen , Xiangyu Zhang , Ninghui Li

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

In recent years, attention-based models have excelled across various domains but remain vulnerable to backdoor attacks, often from downloading or fine-tuning on poisoned datasets. Many current methods to mitigate backdoors in NLP models…

Cryptography and Security · Computer Science 2025-01-07 Yidong Ding , Jiafei Niu , Ping Yi

Training deep neural networks requires gradient estimation from data batches to update parameters. Gradients per parameter are averaged over a set of data and this has been presumed to be safe for privacy-preserving training in joint,…

Machine Learning · Computer Science 2021-04-16 Hongxu Yin , Arun Mallya , Arash Vahdat , Jose M. Alvarez , Jan Kautz , Pavlo Molchanov

The advent of Large Language Models (LLMs) has marked significant achievements in language processing and reasoning capabilities. Despite their advancements, LLMs face vulnerabilities to data poisoning attacks, where the adversary inserts…

Machine Learning · Computer Science 2025-05-30 Xiangyu Zhou , Yao Qiang , Saleh Zare Zade , Mohammad Amin Roshani , Prashant Khanduri , Douglas Zytko , Dongxiao Zhu

As Large Language Models (LLMs) become integral software components in modern applications, unauthorized model derivations through fine-tuning, merging, and redistribution have emerged as critical software engineering challenges. Unlike…

Machine Learning · Computer Science 2025-07-04 Zehao Wu , Yanjie Zhao , Haoyu Wang

Deep Neural Networks (DNNs) are susceptible to backdoor attacks during training. The model corrupted in this way functions normally, but when triggered by certain patterns in the input, produces a predefined target label. Existing defenses…

Cryptography and Security · Computer Science 2022-12-20 Wanlun Ma , Derui Wang , Ruoxi Sun , Minhui Xue , Sheng Wen , Yang Xiang

Neural networks are widely known to be vulnerable to backdoor attacks, a method that poisons a portion of the training data to make the target model perform well on normal data sets, while outputting attacker-specified or random categories…

Computer Vision and Pattern Recognition · Computer Science 2024-06-07 Yong Li , Han Gao