相关论文: Controlling Whisper: Universal Acoustic Adversaria…

As Speech Large Language Models (Speech LLMs) become increasingly integrated into voice-based applications, ensuring their robustness against manipulative or adversarial input becomes critical. Although prior work has studied adversarial…

The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's…

Deep Learning (DL) models have been popular nowadays to execute different speech-related tasks, including automatic speech recognition (ASR). As ASR is being used in different real-time scenarios, it is important that the ASR model remains…

Multi-speaker automatic speech recognition (MS-ASR) faces significant challenges in transcribing overlapped speech, a task critical for applications like meeting transcription and conversational analysis. While serialized output training…

Full-duplex speech interaction, as the most natural and intuitive mode of human communication, is driving artificial intelligence toward more human-like conversational systems. Traditional cascaded speech processing pipelines suffer from…

Pre-trained contextualized language models (PrLMs) have led to strong performance gains in downstream natural language understanding tasks. However, PrLMs can still be easily fooled by adversarial word substitution, which is one of the most…

Although pre-trained language models (PrLMs) have achieved significant success, recent studies demonstrate that PrLMs are vulnerable to adversarial attacks. By generating adversarial examples with slight perturbations on different levels…

We propose a universal adversarial attack on multimodal Large Language Models (LLMs) that leverages a single optimized image to override alignment safeguards across diverse queries and even multiple models. By backpropagating through the…

Large Audio Language Models (LALMs) have significantly advanced audio understanding but introduce critical security risks, particularly through audio jailbreaks. While prior work has focused on English-centric attacks, we expose a far more…

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks…

Pre-training speech models on large volumes of data has achieved remarkable success. OpenAI Whisper is a multilingual multitask model trained on 680k hours of supervised speech data. It generalizes well to various speech recognition and…

While Large Language Models (LLMs) have achieved tremendous success in various applications, they are also susceptible to jailbreaking attacks. Several primary defense strategies have been proposed to protect LLMs from producing harmful…

Recent progress in Automatic Speech Recognition (ASR) has been coupled with a substantial increase in the model sizes, which may now contain billions of parameters, leading to slow inferences even with adapted hardware. In this context,…

Large language models (LLMs) are typically aligned to refuse harmful instructions through safety fine-tuning. A recent attack, termed abliteration, identifies and suppresses the single latent direction most responsible for refusal behavior,…

Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words.…

Automatic reading aloud evaluation can provide valuable support to teachers by enabling more efficient scoring of reading exercises. However, research on reading evaluation systems and applications remains limited. We present a novel…

In a pipeline speech translation system, automatic speech recognition (ASR) system will transmit errors in recognition to the downstream machine translation (MT) system. A standard machine translation system is usually trained on parallel…

Warning: This article includes red-teaming experiments, which contain examples of compromised LLM responses that may be offensive or upsetting. Large Language Models (LLMs) have the potential to create harmful content, such as generating…

Whisper's robust performance in automatic speech recognition (ASR) is often attributed to its massive 680k-hour training set, an impractical scale for most researchers. In this work, we examine how linguistic and acoustic diversity in…

Prompting has become a practical method for utilizing pre-trained language models (LMs). This approach offers several advantages. It allows an LM to adapt to new tasks with minimal training and parameter updates, thus achieving efficiency…