相关论文: Light Commands: Laser-Based Audio Injection Attack…

In this paper we show how two (or more) airgapped computers in the same room, equipped with passive speakers, headphones, or earphones can covertly exchange data via ultrasonic waves. Microphones are not required. Our method is based on the…

The fast advancements in Large Language Models (LLMs) are driving an increasing number of applications. Together with the growing number of users, we also see an increasing number of attackers who try to outsmart these systems. They want…

The area of Machine Learning as a Service (MLaaS) is experiencing increased implementation due to recent advancements in the AI (Artificial Intelligence) industry. However, this spike has prompted concerns regarding AI defense mechanisms,…

Automatic speaker verification systems are increasingly used as the primary means to authenticate costumers. Recently, it has been proposed to train speaker verification systems using end-to-end deep neural models. In this paper, we show…

Deep learning models have achieved high performance on many tasks, and thus have been applied to many security-critical scenarios. For example, deep learning-based face recognition systems have been used to authenticate users to access many…

This paper presents a complete hardware and software pipeline for real-time speech enhancement in noisy and reverberant conditions. The device consists of a microphone array and a camera mounted on eyeglasses, connected to an embedded…

A new method has been developed to adjust volume automatically on all audio devices equipped with at least one microphone, including mobile phones, personal media players, headsets, and car radios, that might be used in noisy environments,…

A vishing attack is a form of social engineering where attackers use phone calls to deceive individuals into disclosing sensitive information, such as personal data, financial information, or security credentials. Attackers exploit the…

Speech enhancement performance degrades significantly in noisy environments, limiting the deployment of speech-controlled technologies in industrial settings, such as manufacturing plants. Existing speech enhancement solutions primarly rely…

We present MetaGuardian, a voice assistant (VA) protection system based on acoustic metamaterials. MetaGuardian can be directly integrated into the enclosures of various smart devices, effectively defending against inaudible, adversarial…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly enhanced the naturalness and flexibility of human computer interaction by enabling seamless understanding across text, vision, and audio modalities. Among these,…

Text-to-speech (TTS) systems offer the opportunity to compensate for a hearing loss at the source rather than correcting for it at the receiving end. This removes limitations such as time constraints for algorithms that amplify a sound in a…

Robotic assistants reduce the manual efforts being put in by humans in their day-to-day tasks. In this paper, we develop a voice-controlled personal assistant robot. The robot takes the human voice commands by its own built-in microphone.…

The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables remarkable capabilities in natural language processing and generation. However, these systems introduce security vulnerabilities that extend beyond…

Interactions based on automatic speech recognition (ASR) have become widely used, with speech input being increasingly utilized to create documents. However, as there is no easy way to distinguish between commands being issued and text…

Physical layer authentication relies on detecting unique imperfections in signals transmitted by radio devices to isolate their fingerprint. Recently, deep learning-based authenticators have increasingly been proposed to classify devices…

Speaker recognition is a popular topic in biometric authentication and many deep learning approaches have achieved extraordinary performances. However, it has been shown in both image and speech applications that deep neural networks are…

Multimodal Large Language Models (MLLMs) integrate vision and text to power applications, but this integration introduces new vulnerabilities. We study Image-based Prompt Injection (IPI), a black-box attack in which adversarial instructions…

Multiple choice questions are at the heart of many standardized tests and examinations at academic institutions allover the world. In this paper, we argue that recent advancements in sensing and human-computer interaction expose these types…

We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to the recognition…