Related papers: Light Commands: Laser-Based Audio Injection Attack…
Whisphone is a novel earbud device designed for speech input via whispering. Utilizing canal-type earbuds with a unique microphone placement at the tip of the earplug, it effectively captures whispered voices radiated in the ear canal…
With the advancement of technology, large language models (LLMs) have achieved remarkable performance across various natural language processing (NLP) tasks, powering LLM-integrated applications like Microsoft Copilot. However, as LLMs…
Accurate face recognition techniques make a series of critical applications possible: policemen could employ it to retrieve criminals' faces from surveillance video streams; cross boarder travelers could pass a face authentication…
Advancements in semiconductor technology have reduced dimensions and cost while improving the performance and capacity of chipsets. In addition, advancement in the AI frameworks and libraries brings possibilities to accommodate more AI at…
The popularity of voice-controlled smart speakers with intelligent personal assistants (IPAs) like the Amazon Echo and their increasing use as an interface for other Internet of Things (IoT) technologies in the home provides opportunities…
The critical challenge of prompt injection attacks in Large Language Models (LLMs) integrated applications, a growing concern in the Artificial Intelligence (AI) field. Such attacks, which manipulate LLMs through natural language inputs,…
This report presents a real-world case study demonstrating how prompt injection can attack large language model platforms such as ChatGPT according to a proposed injection framework. By providing three real-world examples, we show how…
With the increasing popularity of voice-based applications, acoustic eavesdropping has become a serious threat to users' privacy. While on smartphones the access to microphones needs an explicit user permission, acoustic eavesdropping…
A myriad of IoT devices such as bulbs, switches, speakers in a smart home environment allow users to easily control the physical world around them and facilitate their living styles through the sensors already embedded in these devices.…
The main objective of this work is to design and construct a microcomputer based system: to control electric appliances such as light, fan, heater, washing machine, motor, TV, etc. The paper discusses two major approaches to control home…
Logical Access (LA) attacks, also known as audio deepfake attacks, use Text-to-Speech (TTS) or Voice Conversion (VC) methods to generate spoofed speech data. This can represent a serious threat to Automatic Speaker Verification (ASV)…
The fast increase of web services and mobile apps, which collect personal data from users, increases the risk that their privacy may be severely compromised. In particular, the increasing variety of spoken language interfaces and voice…
Recent advances in machine learning and natural language processing have fostered the enormous prosperity of smart voice assistants and their services, e.g., Alexa, Google Home, Siri, etc. However, voice spoofing attacks are deemed to be…
Automatic Speech Recognition (ASR) systems convert speech into text and can be placed into two broad categories: traditional and fully end-to-end. Both types have been shown to be vulnerable to adversarial audio examples that sound benign…
Deep speech classification tasks, including keyword spotting and speaker verification, are vital in speech-based human-computer interaction. Recently, the security of these technologies has been revealed to be susceptible to backdoor…
Recent advancements have led to the widespread adoption of code-oriented large language models (Code LLMs) for programming tasks. Despite their success in deployment, their security research is left far behind. This paper introduces a new…
Due to the widespread deployment of fingerprint/face/speaker recognition systems, attacking deep learning based biometric systems has drawn more and more attention. Previous research mainly studied the attack to the vision-based system,…
Speaker verification has been widely and successfully adopted in many mission-critical areas for user identification. The training of speaker verification requires a large amount of data, therefore users usually need to adopt third-party…
Vision-Language Models (VLMs) are increasingly deployed in consumer applications where users seek recommendations about products, dining, and services. We introduce Hidden Ads, a new class of backdoor attacks that exploit this…
In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to…