English
Related papers

Related papers: STEP: Detecting Audio Backdoor Attacks via Stabili…

200 papers

Federated learning, an innovative network architecture designed to safeguard user privacy, is gaining widespread adoption in the realm of technology. However, given the existence of backdoor attacks in federated learning, exploring the…

Cryptography and Security · Computer Science 2024-08-27 Weida Xu , Yang Xu , Sicong Zhang

Data-driven software engineering processes, such as vulnerability prediction heavily rely on the quality of the data used. In this paper, we observe that it is infeasible to obtain a noise-free security defect dataset in practice. Despite…

Software Engineering · Computer Science 2022-04-04 Roland Croft , M. Ali Babar , Huaming Chen

Deep speech classification tasks, mainly including keyword spotting and speaker verification, play a crucial role in speech-based human-computer interaction. Recently, the security of these technologies has been demonstrated to be…

Sound · Computer Science 2024-09-09 Wenhan Yao , Zedong XingXiarun Chen , Jia Liu , yongqiang He , Weiping Wen

Backdoor attacks mislead machine-learning models to output an attacker-specified class when presented a specific trigger at test time. These attacks require poisoning the training data to compromise the learning algorithm, e.g., by…

Machine Learning · Computer Science 2021-11-03 Kathrin Grosse , Taesung Lee , Battista Biggio , Youngja Park , Michael Backes , Ian Molloy

The training phase of machine learning models is a delicate step, especially in cybersecurity contexts. Recent research has surfaced a series of insidious training-time attacks that inject backdoors in models designed for security…

Cryptography and Security · Computer Science 2025-05-06 Giorgio Severi , Simona Boboila , John Holodnak , Kendra Kratkiewicz , Rauf Izmailov , Michael J. De Lucia , Alina Oprea

Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show…

Audio and Speech Processing · Electrical Eng. & Systems 2020-09-16 Tejas Jayashankar , Jonathan Le Roux , Pierre Moulin

Recent studies have proposed integrating Chain-of-Thought (CoT) reasoning to further enhance the reliability of Code Language Models (CLMs) in generating code, a step-by-step approach that breaks down complex programming tasks into…

Software Engineering · Computer Science 2025-03-11 Naizhu Jin , Zhong Li , Yinggang Guo , Chao Su , Tian Zhang , Qingkai Zeng

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

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

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data.…

Sound · Computer Science 2022-07-12 Haoxin Ma , Jiangyan Yi , Jianhua Tao , Ye Bai , Zhengkun Tian , Chenglong Wang

Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i.e., sever and clients only hold partial sub-networks and exchange…

Machine Learning · Computer Science 2023-07-19 Mingyuan Fan , Cen Chen , Chengyu Wang , Wenmeng Zhou , Jun Huang

Language models are often at risk of diverse backdoor attacks, especially data poisoning. Thus, it is important to investigate defense solutions for addressing them. Existing backdoor defense methods mainly focus on backdoor attacks with…

Computation and Language · Computer Science 2024-04-04 Qin Liu , Fei Wang , Chaowei Xiao , Muhao Chen

In this paper, we evaluate deep learning-enabled AED systems against evasion attacks based on adversarial examples. We test the robustness of multiple security critical AED tasks, implemented as CNNs classifiers, as well as existing…

Sound · Computer Science 2021-11-11 Rodrigo dos Santos , Shirin Nilizadeh

Backdoor attacks are a kind of emergent security threat in deep learning. After being injected with a backdoor, a deep neural model will behave normally on standard inputs but give adversary-specified predictions once the input contains…

Cryptography and Security · Computer Science 2022-10-20 Yangyi Chen , Fanchao Qi , Hongcheng Gao , Zhiyuan Liu , Maosong Sun

Backdoor attack against deep neural networks is currently being profoundly investigated due to its severe security consequences. Current state-of-the-art backdoor attacks require the adversary to modify the input, usually by adding a…

Cryptography and Security · Computer Science 2020-10-09 Ahmed Salem , Michael Backes , Yang Zhang

Text-to-image diffusion models are increasingly vulnerable to backdoor attacks, where malicious modifications to the training data cause the model to generate unintended outputs when specific triggers are present. While classification…

Cryptography and Security · Computer Science 2025-04-29 Abha Jha , Ashwath Vaithinathan Aravindan , Matthew Salaway , Atharva Sandeep Bhide , Duygu Nur Yaldiz

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

Outsourced training and machine learning as a service have resulted in novel attack vectors like backdoor attacks. Such attacks embed a secret functionality in a neural network activated when the trigger is added to its input. In most works…

Cryptography and Security · Computer Science 2022-11-08 Stefanos Koffas , Stjepan Picek , Mauro Conti

Existing dialogue datasets contain lots of noise in their state annotations. Such noise can hurt model training and ultimately lead to poor generalization performance. A general framework named ASSIST has recently been proposed to train…

Computation and Language · Computer Science 2022-10-25 Fanghua Ye , Xi Wang , Jie Huang , Shenghui Li , Samuel Stern , Emine Yilmaz

In a backdoor attack, an adversary injects corrupted data into a model's training dataset in order to gain control over its predictions on images with a specific attacker-defined trigger. A typical corrupted training example requires…

Machine Learning · Computer Science 2023-10-31 Rishi D. Jha , Jonathan Hayase , Sewoong Oh