English
Related papers

Related papers: Eliminating Backdoors in Neural Code Models for Se…

200 papers

The financial industry relies on deep learning models for making important decisions. This adoption brings new danger, as deep black-box models are known to be vulnerable to adversarial attacks. In computer vision, one can shape the output…

Machine Learning · Computer Science 2024-08-27 Alina Ermilova , Elizaveta Kovtun , Dmitry Berestnev , Alexey Zaytsev

Explainable machine learning holds great potential for analyzing and understanding learning-based systems. These methods can, however, be manipulated to present unfaithful explanations, giving rise to powerful and stealthy adversaries. In…

Cryptography and Security · Computer Science 2022-04-21 Maximilian Noppel , Lukas Peter , Christian Wressnegger

Creating a state-of-the-art deep-learning system requires vast amounts of data, expertise, and hardware, yet research into embedding copyright protection for neural networks has been limited. One of the main methods for achieving such…

Cryptography and Security · Computer Science 2020-04-27 William Aiken , Hyoungshick Kim , Simon Woo

The advent of clinical language models integrated into electronic health records (EHR) for clinical decision support has marked a significant advancement, leveraging the depth of clinical notes for improved decision-making. Despite their…

Computation and Language · Computer Science 2024-07-09 Weimin Lyu , Zexin Bi , Fusheng Wang , Chao Chen

Federated Learning (FL) allows multiple clients to collaboratively train a Neural Network (NN) model on their private data without revealing the data. Recently, several targeted poisoning attacks against FL have been introduced. These…

Cryptography and Security · Computer Science 2022-01-04 Phillip Rieger , Thien Duc Nguyen , Markus Miettinen , Ahmad-Reza Sadeghi

The backdoor attack poses a new security threat to deep neural networks. Existing backdoor often relies on visible universal trigger to make the backdoored model malfunction, which are not only usually visually suspicious to human but also…

Cryptography and Security · Computer Science 2024-12-24 Xiangqi Wang , Mingfu Xue , Kewei Chen , Jing Xu , Wenmao Liu , Leo Yu Zhang , Yushu Zhang

Backdoor attacks allow an attacker to embed functionality jeopardizing proper behavior of any algorithm, machine learning or not. This hidden functionality can remain inactive for normal use of the algorithm until activated by the attacker.…

Computer Vision and Pattern Recognition · Computer Science 2022-08-23 Alexander Unnervik , Sébastien Marcel

Backdoor (Trojan) attack is a common threat to deep neural networks, where samples from one or more source classes embedded with a backdoor trigger will be misclassified to adversarial target classes. Existing methods for detecting whether…

Machine Learning · Computer Science 2023-11-17 Zhen Xiang , Zidi Xiong , Bo Li

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

While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it inadvertently exposes a new attack surface for backdoor attacks. Existing CoT backdoor attacks…

Cryptography and Security · Computer Science 2026-04-14 Yizhe Zeng , Wei Zhang , Yunpeng Li , Juxin Xiao , Xiao Wang , Yuling Liu

Backdoor attacks pose a new threat to NLP models. A standard strategy to construct poisoned data in backdoor attacks is to insert triggers (e.g., rare words) into selected sentences and alter the original label to a target label. This…

Computation and Language · Computer Science 2022-04-28 Leilei Gan , Jiwei Li , Tianwei Zhang , Xiaoya Li , Yuxian Meng , Fei Wu , Yi Yang , Shangwei Guo , Chun Fan

Pre-trained models (PTMs) have been widely used in various downstream tasks. The parameters of PTMs are distributed on the Internet and may suffer backdoor attacks. In this work, we demonstrate the universal vulnerability of PTMs, where…

Computation and Language · Computer Science 2023-10-23 Zhengyan Zhang , Guangxuan Xiao , Yongwei Li , Tian Lv , Fanchao Qi , Zhiyuan Liu , Yasheng Wang , Xin Jiang , Maosong Sun

With the development of technology, large language models (LLMs) have dominated the downstream natural language processing (NLP) tasks. However, because of the LLMs' instruction-following abilities and inability to distinguish the…

Cryptography and Security · Computer Science 2025-10-07 Yulin Chen , Haoran Li , Yuan Sui , Yangqiu Song , Bryan Hooi

While previous research backdoored neural networks by changing their parameters, recent work uncovered a more insidious threat: backdoors embedded within the definition of the network's architecture. This involves injecting common…

Cryptography and Security · Computer Science 2024-02-13 Harry Langford , Ilia Shumailov , Yiren Zhao , Robert Mullins , Nicolas Papernot

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

Given the power of vision transformers, a new learning paradigm, pre-training and then prompting, makes it more efficient and effective to address downstream visual recognition tasks. In this paper, we identify a novel security threat…

Computer Vision and Pattern Recognition · Computer Science 2024-05-20 Sheng Yang , Jiawang Bai , Kuofeng Gao , Yong Yang , Yiming Li , Shu-tao Xia

A backdoor deep learning (DL) model behaves normally upon clean inputs but misbehaves upon trigger inputs as the backdoor attacker desires, posing severe consequences to DL model deployments. State-of-the-art defenses are either limited to…

Cryptography and Security · Computer Science 2021-11-23 Yinshan Li , Hua Ma , Zhi Zhang , Yansong Gao , Alsharif Abuadbba , Anmin Fu , Yifeng Zheng , Said F. Al-Sarawi , Derek Abbott

Large language models (LLMs) have revolutionized software development practices, yet concerns about their safety have arisen, particularly regarding hidden backdoors, aka trojans. Backdoor attacks involve the insertion of triggers into…

Software Engineering · Computer Science 2024-03-06 Aftab Hussain , Md Rafiqul Islam Rabin , Navid Ayoobi , Mohammad Amin Alipour

Graph Neural Networks (GNNs) are a class of deep learning models capable of processing graph-structured data, and they have demonstrated significant performance in a variety of real-world applications. Recent studies have found that GNN…

Machine Learning · Computer Science 2025-05-07 Jiazhu Dai , Haoyu Sun

Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where hidden features (patterns) trained to a normal model, which is only activated by some specific input (called triggers), trick the model into producing…

Cryptography and Security · Computer Science 2020-09-01 Shaofeng Li , Minhui Xue , Benjamin Zi Hao Zhao , Haojin Zhu , Xinpeng Zhang