相关论文: Enabling Fast and Universal Audio Adversarial Atta…

Adversarial machine learning research has recently demonstrated the feasibility to confuse automatic speech recognition (ASR) models by introducing acoustically imperceptible perturbations to audio samples. To help researchers and…

Deep Neural Networks (DNNs) are notoriously vulnerable to adversarial input designs with limited noise budgets. While numerous successful attacks with subtle modifications to original input have been proposed, defense techniques against…

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

In this paper, we compare different audio signal representations, including the raw audio waveform and a variety of time-frequency representations, for the task of audio synthesis with Generative Adversarial Networks (GANs). We conduct the…

Audio codecs are typically transform-domain based and efficiently code stationary audio signals, but they struggle with speech and signals containing dense transient events such as applause. Specifically, with these two classes of signals…

With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial examples are generated on specific individual models,…

Generative adversarial nets (GAN) has been successfully introduced for generating text to alleviate the exposure bias. However, discriminators in these models only evaluate the entire sequence, which causes feedback sparsity and mode…

Jailbreak attacks to Large audio-language models (LALMs) are studied recently, but they exclusively focused on the attack scenario where the adversary can fully manipulate user prompts (named strong adversary) and limited in effectiveness,…

Existing generative adversarial network (GAN) based conditional image generative models typically produce fixed output for the same conditional input, which is unreasonable for highly subjective tasks, such as large-mask image inpainting or…

Synthetic creation of drum sounds (e.g., in drum machines) is commonly performed using analog or digital synthesis, allowing a musician to sculpt the desired timbre modifying various parameters. Typically, such parameters control low-level…

Despite recent progress in generative adversarial network (GAN)-based vocoders, where the model generates raw waveform conditioned on acoustic features, it is challenging to synthesize high-fidelity audio for numerous speakers across…

Many problems in database systems, such as cardinality estimation, database testing and optimizer tuning, require a large query load as data. However, it is often difficult to obtain a large number of real queries from users due to user…

Robust speaker recognition, including in the presence of malicious attacks, is becoming increasingly important and essential, especially due to the proliferation of several smart speakers and personal agents that interact with an…

The paper presents a novel approach of spoofing wireless signals by using a general adversarial network (GAN) to generate and transmit synthetic signals that cannot be reliably distinguished from intended signals. It is of paramount…

Compared to single-target adversarial attacks, multi-target attacks have garnered significant attention due to their ability to generate adversarial images for multiple target classes simultaneously. However, existing generative approaches…

In this paper, we address the challenge of speech enhancement in real-world recordings, which often contain various forms of distortion, such as background noise, reverberation, and microphone artifacts. We revisit the use of Generative…

LLMs have shown impressive capabilities across various natural language processing tasks, yet remain vulnerable to input prompts, known as jailbreak attacks, carefully designed to bypass safety guardrails and elicit harmful responses.…

We design, implement, and evaluate adversarial decoding, a new, generic text generation technique that produces readable documents for different adversarial objectives. Prior methods either produce easily detectable gibberish, or cannot…

Deep neural networks have been successfully applied in various machine learning tasks. However, studies show that neural networks are susceptible to adversarial attacks. This exposes a potential threat to neural network-based intelligent…

Recent studies identify that Deep learning Neural Networks (DNNs) are vulnerable to subtle perturbations, which are not perceptible to human visual system but can fool the DNN models and lead to wrong outputs. A class of adversarial attack…