Related papers: Codec-Robust Attacks on Audio LLMs
Although end-to-end automatic speech recognition (e2e ASR) models are widely deployed in many applications, there have been very few studies to understand models' robustness against adversarial perturbations. In this paper, we explore…
Multimodal large language models (MLLMs), which bridge the gap between audio-visual and natural language processing, achieve state-of-the-art performance on several audio-visual tasks. Despite the superior performance of MLLMs, the scarcity…
Vision-language pre-training models (VLPs) demonstrate strong multimodal understanding and zero-shot generalization, yet remain vulnerable to adversarial examples, raising concerns about their reliability. Recent work, Test-Time…
Large language model (LLM) watermarking has shown promise in detecting AI-generated content and mitigating misuse, with prior work claiming robustness against paraphrasing and text editing. In this paper, we argue that existing evaluations…
Audio watermarking has been widely applied in copyright protection and source tracing. However, due to the inherent characteristics of audio signals, watermark localization and resistance to desynchronization attacks remain significant…
The emergence of audio language models is empowered by neural audio codecs, which establish critical mappings between continuous waveforms and discrete tokens compatible with language model paradigms. The evolutionary trends from…
Most widely-used modern audio codecs, such as Ogg Vorbis and MP3, as well as more recent "neural" codecs like Meta's Encodec or the Descript Audio Codec are based on block-coding; audio is divided into overlapping, fixed-size "frames" which…
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…
This paper introduces a novel adversarial algorithm for attacking the state-of-the-art speech-to-text systems, namely DeepSpeech, Kaldi, and Lingvo. Our approach is based on developing an extension for the conventional distortion condition…
Automatic Speaker Verification (ASV) systems can be used for voice-enabled applications for identity verification. However, recent studies have exposed these systems' vulnerabilities to both over-the-line (OTL) and over-the-air (OTA)…
Text-to-audio (TTA) system has recently gained attention for its ability to synthesize general audio based on text descriptions. However, previous studies in TTA have limited generation quality with high computational costs. In this study,…
Recent techniques such as retrieval-augmented generation or chain-of-thought reasoning have led to longer contexts and increased inference costs. Context compression techniques can reduce these costs, but the most effective approaches…
Various adversarial audio attacks have recently been developed to fool automatic speech recognition (ASR) systems. We here propose a defense against such attacks based on the uncertainty introduced by dropout in neural networks. We show…
Large language models (LLMs) have achieved impressive performance across natural language tasks and are increasingly deployed in real-world applications. Despite extensive safety alignment efforts, recent studies show that such alignment is…
Recent improvements in neural audio codec (NAC) models have generated interest in adopting pre-trained codecs for a variety of speech processing applications to take advantage of the efficiencies gained from high compression, but these have…
Beyond the success story of adversarial training (AT) in the recent text domain on top of pre-trained language models (PLMs), our empirical study showcases the inconsistent gains from AT on some tasks, e.g. commonsense reasoning, named…
Millimeter-wave (mmWave) and terahertz (THz) massive MIMO systems often rely on predefined beamforming codebooks, which are usually suboptimal in Non-Line-of-Sight (NLoS) conditions and for hardware-limited transceivers. Reinforcement…
This paper explores the integration of model-based and data-driven approaches within the realm of neural speech and audio coding systems. It highlights the challenges posed by the subjective evaluation processes of speech and audio codecs…
We introduce the Lossy Implicit Network Activation Coding (LINAC) defence, an input transformation which successfully hinders several common adversarial attacks on CIFAR-$10$ classifiers for perturbations up to $\epsilon = 8/255$ in…
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…