6 accepted papers
Machine learning approaches for speech enhancement are becoming increasingly expressive, enabling ever more powerful modifications of input signals. In this paper, we demonstrate that this expressiveness introduces a vulnerability: advanced speech enhancement models can be susceptible to adversarial…
Evaluating the adversarial robustness of deep networks to gradient-based attacks is challenging. While most attacks consider $\ell_2$- and $\ell_\infty$-norm constraints to craft input perturbations, only a few investigate sparse $\ell_1$- and $\ell_0$-norm attacks. In particular, $\ell_0$-norm atta…
There is a growing interest in using Large Language Models (LLMs) in multi-agent systems to tackle interactive real-world tasks that require effective collaboration and assessing complex situations. Yet, we have a limited understanding of LLMs' communication and decision-making abilities in multi-ag…
Large language model systems face significant security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in th…
Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes'' has emerged. This research most often focuses on the image domain, while studies exploring generated audio signals have---so-far---b…
Deep neural networks can generate images that are astonishingly realistic, so much so that it is often hard for humans to distinguish them from actual photos. These achievements have been largely made possible by Generative Adversarial Networks (GANs). While deep fake images have been thoroughly inv…