相关论文: When Good Sounds Go Adversarial: Jailbreaking Audi…

Machine Learning systems are vulnerable to adversarial attacks and will highly likely produce incorrect outputs under these attacks. There are white-box and black-box attacks regarding to adversary's access level to the victim learning…

Adversarial attacks pose a severe security threat to the state-of-the-art speaker identification systems, thereby making it vital to propose countermeasures against them. Building on our previous work that used representation learning to…

We propose WHISPER-GPT: A generative large language model (LLM) for speech and music that allows us to work with continuous audio representations and discrete tokens simultaneously as part of a single architecture. There has been a huge…

Advances in deep learning have enabled a wide range of promising applications. However, these systems are vulnerable to Adversarial Machine Learning (AML) attacks; adversarially crafted perturbations to their inputs could cause them to…

Current large language models (LLMs) provide a strong foundation for large-scale user-oriented natural language tasks. A large number of users can easily inject adversarial text or instructions through the user interface, thus causing LLMs…

In this paper, we propose PhantomSound, a query-efficient black-box attack toward voice assistants. Existing black-box adversarial attacks on voice assistants either apply substitution models or leverage the intermediate model output to…

Large language models (LLMs) are increasingly deployed in multi-agent systems where agents communicate in natural language to solve tasks jointly. A key capability in such systems is consensus formation, where agents iteratively exchange…

Large Language Models (LLMs) have demonstrated great capabilities in natural language understanding and generation, largely attributed to the intricate alignment process using human feedback. While alignment has become an essential training…

Evaluations of large language model (LLM) risks and capabilities are increasingly being incorporated into AI risk management and governance frameworks. Currently, most risk evaluations are conducted by designing inputs that elicit harmful…

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety…

Large Language Models (LLMs) have demonstrated exceptional performance across various tasks, but their security vulnerabilities can be exploited by attackers to generate harmful content, causing adverse impacts across various societal…

Jailbreak attacks on multimodal AI systems remain underexplored, even though unsafe image generation can have more severe consequences than unsafe text and current defenses are relatively immature. We introduce PAST2HARM, a simple yet…

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

We construct targeted audio adversarial examples on automatic speech recognition. Given any audio waveform, we can produce another that is over 99.9% similar, but transcribes as any phrase we choose (recognizing up to 50 characters per…

As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited work has explored this issue in depth. This paper explores…

Thanks to the popularisation of transformer-based models, speech recognition (SR) is gaining traction in various application fields, such as industrial and robotics environments populated with mission-critical devices. While…

The deployment of artificial intelligence (AI) in critical decision-making and evaluation processes raises concerns about inherent biases that malicious actors could exploit to distort decision outcomes. We propose a systematic method to…

The foundational capabilities established by Large Language Models (LLMs) have paved the way for Multimodal Large Language Models (MLLMs), within which Large Audio Language Models (LALMs) are essential for realizing universal auditory…

Smart speakers and voice-based virtual assistants are core components for the success of the IoT paradigm. Unfortunately, they are vulnerable to various privacy threats exploiting machine learning to analyze the generated encrypted traffic.…

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease a victim's cumulative expected reward by manipulating the victim's observations. Despite the efficiency of previous optimization-based methods for…