Related papers: Breaking Speaker Recognition with PaddingBack

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS).…

Deep learning is an emerging technology that is considered one of the most promising directions for reaching higher levels of artificial intelligence. Among the other achievements, building computers that understand speech represents a…

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample-wise to more fine-grained sentence element-wise (e.g.,…

The tremendous progress of autoencoders and generative adversarial networks (GANs) has led to their application to multiple critical tasks, such as fraud detection and sanitized data generation. This increasing adoption has fostered the…

Vision Language Models (VLMs) have shown remarkable performance, but are also vulnerable to backdoor attacks whereby the adversary can manipulate the model's outputs through hidden triggers. Prior attacks primarily rely on single-modality…

The development of deep learning technology has greatly promoted the performance improvement of automatic speech recognition (ASR) technology, which has demonstrated an ability comparable to human hearing in many tasks. Voice interfaces are…

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

Backdoor attacks, which maliciously control a well-trained model's outputs of the instances with specific triggers, are recently shown to be serious threats to the safety of reusing deep neural networks (DNNs). In this work, we propose an…

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

The rapid growth of natural language processing (NLP) and pre-trained language models have enabled accurate text classification in a variety of settings. However, text classification models are susceptible to backdoor attacks, where an…

Machine learning is being increasingly used by individuals, research institutions, and corporations. This has resulted in the surge of Machine Learning-as-a-Service (MLaaS) - cloud services that provide (a) tools and resources to learn the…

Data Distribution Service (DDS) is an innovative approach towards communication in ICS/IoT infrastructure and robotics. Being based on the cross-platform and cross-language API to be applicable in any computerised device, it offers the…

Deep learning (DL) has been widely studied for assisting applications of modern wireless communications. One of the applications is automatic modulation classification (AMC). However, DL models are found to be vulnerable to adversarial…

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…

Speech and speaker recognition systems are employed in a variety of applications, from personal assistants to telephony surveillance and biometric authentication. The wide deployment of these systems has been made possible by the improved…

The challenge of WAD (web attack detection) is growing as hackers continuously refine their methods to evade traditional detection. Deep learning models excel in handling complex unknown attacks due to their strong generalization and…

The rise of multimodal large language models has introduced innovative human-machine interaction paradigms but also significant challenges in machine learning safety. Audio-Language Models (ALMs) are especially relevant due to the intuitive…

The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…

Voice Recognition Systems (VRSs) employ deep learning for speech recognition and speaker recognition. They have been widely deployed in various real-world applications, from intelligent voice assistance to telephony surveillance and…

Recent advances in Machine Learning (ML) have opened up new avenues for its extensive use in real-world applications. Facial recognition, specifically, is used from simple friend suggestions in social-media platforms to critical security…