English
Related papers

Related papers: Mitigating Backdoor Triggered and Targeted Data Po…

200 papers

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

Defenses against security threats have been an interest of recent studies. Recent works have shown that it is not difficult to attack a natural language processing (NLP) model while defending against them is still a cat-mouse game. Backdoor…

Cryptography and Security · Computer Science 2022-05-31 Sangeet Sagar , Abhinav Bhatt , Abhijith Srinivas Bidaralli

Speaker verification has been widely used in many authentication scenarios. However, training models for speaker verification requires large amounts of data and computing power, so users often use untrustworthy third-party data or deploy…

Cryptography and Security · Computer Science 2025-02-05 Haodong Zhao , Wei Du , Junjie Guo , Gongshen Liu

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper…

Cryptography and Security · Computer Science 2026-02-03 Miao Lin , Feng Yu , Rui Ning , Lusi Li , Jiawei Chen , Qian Lou , Mengxin Zheng , Chunsheng Xin , Hongyi Wu

Backdoor attacks involve the injection of a limited quantity of poisoned examples containing triggers into the training dataset. During the inference stage, backdoor attacks can uphold a high level of accuracy for normal examples, yet when…

Cryptography and Security · Computer Science 2024-06-25 Hanfeng Xia , Haibo Hong , Ruili Wang

Voice Authentication Systems (VAS) use unique vocal characteristics for verification. They are increasingly integrated into high-security sectors such as banking and healthcare. Despite their improvements using deep learning, they face…

Sound · Computer Science 2026-01-12 Kamel Kamel , Hridoy Sankar Dutta , Keshav Sood , Sunil Aryal

Adversarial audio attacks can be considered as a small perturbation unperceptive to human ears that is intentionally added to the audio signal and causes a machine learning model to make mistakes. This poses a security concern about the…

Machine Learning · Computer Science 2019-11-26 Mohammad Esmaeilpour , Patrick Cardinal , Alessandro Lameiras Koerich

With the growing use of voice-activated systems and speech recognition technologies, the danger of backdoor attacks on audio data has grown significantly. This research looks at a specific type of attack, known as a Stochastic…

Cryptography and Security · Computer Science 2025-04-28 Orson Mengara

3D deep learning has been increasingly more popular for a variety of tasks including many safety-critical applications. However, recently several works raise the security issues of 3D deep models. Although most of them consider adversarial…

Machine Learning · Computer Science 2025-05-09 Xinke Li , Zhirui Chen , Yue Zhao , Zekun Tong , Yabang Zhao , Andrew Lim , Joey Tianyi Zhou

This work explores an emerging security threat against deep neural networks (DNNs) based image classification, i.e., backdoor attack. In this scenario, the attacker aims to inject a backdoor into the model by manipulating training data,…

Cryptography and Security · Computer Science 2024-12-03 Zhengyao Song , Yongqiang Li , Danni Yuan , Li Liu , Shaokui Wei , Baoyuan Wu

The impact of voice disorders is becoming more widely acknowledged as a public health issue. Several machine learning-based classifiers with the potential to identify disorders have been used in recent studies to differentiate between…

Cryptography and Security · Computer Science 2024-10-23 Gianpaolo Perelli , Andrea Panzino , Roberto Casula , Marco Micheletto , Giulia Orrù , Gian Luca Marcialis

Backdoor attacks pose a serious threat to the security of large language models (LLMs), causing them to exhibit anomalous behavior under specific trigger conditions. The design of backdoor triggers has evolved from fixed triggers to dynamic…

Cryptography and Security · Computer Science 2026-04-15 Haotian Jin , Yang Li , Haihui Fan , Lin Shen , Xiangfang Li , Bo Li

Voice Authentication (VA), also known as Automatic Speaker Verification (ASV), is a widely adopted authentication method, particularly in automated systems like banking services, where it serves as a secondary layer of user authentication.…

Cryptography and Security · Computer Science 2025-02-14 Eshaq Jamdar , Amith Kamath Belman

A number of studies have successfully developed speaker verification or presentation attack detection systems. However, studies integrating the two tasks remain in the preliminary stages. In this paper, we propose two approaches for…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-29 Hye-jin Shim , Jee-weon Jung , Ju-ho Kim , Seung-bin Kim , Ha-Jin Yu

Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most versatile and…

Cryptography and Security · Computer Science 2024-04-22 Beichen Li , Yuanfang Guo , Heqi Peng , Yangxi Li , Yunhong Wang

Recent studies have widely investigated backdoor attacks on Large Language Models (LLMs) by inserting harmful question-answer (QA) pairs into their training data. However, we revisit existing attacks and identify two critical limitations:…

Computation and Language · Computer Science 2025-10-07 Jiawei Kong , Hao Fang , Xiaochen Yang , Kuofeng Gao , Bin Chen , Shu-Tao Xia , Ke Xu , Han Qiu

This work explores backdoor attacks for automatic speech recognition systems where we inject inaudible triggers. By doing so, we make the backdoor attack challenging to detect for legitimate users, and thus, potentially more dangerous. We…

Cryptography and Security · Computer Science 2023-05-30 Stefanos Koffas , Jing Xu , Mauro Conti , Stjepan Picek

Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model…

Machine Learning · Computer Science 2021-06-18 Avi Schwarzschild , Micah Goldblum , Arjun Gupta , John P Dickerson , Tom Goldstein

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

Multimodal large language models have become an important infrastructure for unified processing of visual and linguistic tasks. However, such models are highly susceptible to backdoor implantation during supervised fine-tuning and will…

Computer Vision and Pattern Recognition · Computer Science 2026-04-07 Tianmeng Fang , Yong Wang , Zetai Kong , Zengzhen Su , Jun Wang , Chengjin Yu , Wei Wang