English
Related papers

Related papers: Task-Agnostic Detector for Insertion-Based Backdoo…

200 papers

Backdoor attacks pose a severe threat to deep learning, yet their impact on object detection remains poorly understood compared to image classification. While attacks have been proposed, we identify critical weaknesses in existing…

Computer Vision and Pattern Recognition · Computer Science 2026-01-30 Kealan Dunnett , Reza Arablouei , Dimity Miller , Volkan Dedeoglu , Raja Jurdak

Backdoor attacks compromise model reliability by using triggers to manipulate outputs. Trigger inversion can accurately locate these triggers via a generator and is therefore critical for backdoor defense. However, the discrete nature of…

Cryptography and Security · Computer Science 2026-03-18 Ruyi Zhang , Heng Gao , Songlei Jian , Yusong Tan , Haifang Zhou

Backdoor attack poses a significant security threat to Deep Learning applications. Existing attacks are often not evasive to established backdoor detection techniques. This susceptibility primarily stems from the fact that these attacks…

Computer Vision and Pattern Recognition · Computer Science 2024-03-27 Siyuan Cheng , Guanhong Tao , Yingqi Liu , Guangyu Shen , Shengwei An , Shiwei Feng , Xiangzhe Xu , Kaiyuan Zhang , Shiqing Ma , Xiangyu Zhang

Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on the texts with triggers that…

Computation and Language · Computer Science 2023-12-27 Xuan Sheng , Zhicheng Li , Zhaoyang Han , Xiangmao Chang , Piji Li

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

Backdoor attacks allow an attacker to embed a specific vulnerability in a machine learning algorithm, activated when an attacker-chosen pattern is presented, causing a specific misprediction. The need to identify backdoors in biometric…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Alexander Unnervik , Hatef Otroshi Shahreza , Anjith George , Sébastien Marcel

Pre-trained language models allowed us to process downstream tasks with the help of fine-tuning, which aids the model to achieve fairly high accuracy in various Natural Language Processing (NLP) tasks. Such easily-downloaded language models…

Computation and Language · Computer Science 2022-11-22 Jaechul Roh , Minhao Cheng , Yajun Fang

Text anomaly detection is crucial for identifying spam, misinformation, and offensive language in natural language processing tasks. Despite the growing adoption of embedding-based methods, their effectiveness and generalizability across…

Computation and Language · Computer Science 2025-05-26 Yang Cao , Sikun Yang , Chen Li , Haolong Xiang , Lianyong Qi , Bo Liu , Rongsheng Li , Ming Liu

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

Although pre-training achieves remarkable performance, it suffers from task-agnostic backdoor attacks due to vulnerabilities in data and training mechanisms. These attacks can transfer backdoors to various downstream tasks. In this paper,…

Cryptography and Security · Computer Science 2025-03-04 Pengzhou Cheng , Wei Du , Zongru Wu , Fengwei Zhang , Libo Chen , Zhuosheng Zhang , Gongshen Liu

As deep neural networks power increasingly critical applications, stealthy backdoor attacks, where poisoned training inputs trigger malicious model behaviour while appearing benign, pose a severe security risk. Many existing defences are…

Machine Learning · Computer Science 2025-10-17 Nam Le , Leo Yu Zhang , Kewen Liao , Shirui Pan , Wei Luo

Natural language processing (NLP) systems have been proven to be vulnerable to backdoor attacks, whereby hidden features (backdoors) are trained into a language model and may only be activated by specific inputs (called triggers), to trick…

Computation and Language · Computer Science 2021-09-29 Shaofeng Li , Hui Liu , Tian Dong , Benjamin Zi Hao Zhao , Minhui Xue , Haojin Zhu , Jialiang Lu

Adversarial attacks on Graph Neural Networks (GNNs) reveal their security vulnerabilities, limiting their adoption in safety-critical applications. However, existing attack strategies rely on the knowledge of either the GNN model being used…

Machine Learning · Computer Science 2022-12-09 Kartik Sharma , Samidha Verma , Sourav Medya , Arnab Bhattacharya , Sayan Ranu

Pre-trained language models have achieved remarkable success across a wide range of natural language processing (NLP) tasks, particularly when fine-tuned on large, domain-relevant datasets. However, they remain vulnerable to backdoor…

Computation and Language · Computer Science 2026-02-02 Anindya Sundar Das , Kangjie Chen , Monowar Bhuyan

With extensive studies on backdoor attack and detection, still fundamental questions are left unanswered regarding the limits in the adversary's capability to attack and the defender's capability to detect. We believe that answers to these…

Cryptography and Security · Computer Science 2022-10-14 Di Tang , Rui Zhu , XiaoFeng Wang , Haixu Tang , Yi Chen

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

Backdoor data detection is traditionally studied in an end-to-end supervised learning (SL) setting. However, recent years have seen the proliferating adoption of self-supervised learning (SSL) and transfer learning (TL), due to their lesser…

Machine Learning · Computer Science 2023-08-08 Minzhou Pan , Yi Zeng , Lingjuan Lyu , Xue Lin , Ruoxi Jia

We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense falls within the category of post-development defenses that…

Cryptography and Security · Computer Science 2023-10-06 Tinghao Xie , Xiangyu Qi , Ping He , Yiming Li , Jiachen T. Wang , Prateek Mittal

Recent studies have revealed that \textit{Backdoor Attacks} can threaten the safety of natural language processing (NLP) models. Investigating the strategies of backdoor attacks will help to understand the model's vulnerability. Most…

Machine Learning · Computer Science 2023-10-26 Weimin Lyu , Songzhu Zheng , Lu Pang , Haibin Ling , Chao Chen

Recent foundation models for tabular data achieve strong task-specific performance via in-context learning. Nevertheless, they focus on direct prediction by encapsulating both representation learning and task-specific inference inside a…

Machine Learning · Computer Science 2026-02-05 Frederik Hoppe , Lars Kleinemeier , Astrid Franz , Udo Göbel