Related papers: Decoding Deception: Understanding Automatic Speech…

In this paper, we evaluate deep learning-enabled AED systems against evasion attacks based on adversarial examples. We test the robustness of multiple security critical AED tasks, implemented as CNNs classifiers, as well as existing…

We propose the first character-level white-box adversarial attack method against transformer models. The intuition of our method comes from the observation that words are split into subtokens before being fed into the transformer models and…

Audio deepfakes pose significant threats, including impersonation, fraud, and reputation damage. To address these risks, audio deepfake detection (ADD) techniques have been developed, demonstrating success on benchmarks like ASVspoof2019.…

Neural networks are vulnerable to adversarial examples, which are malicious inputs crafted to fool pre-trained models. Adversarial examples often exhibit black-box attacking transferability, which allows that adversarial examples crafted…

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks. Specifically, we propose a poisoning attack in which a…

Continual learning algorithms are typically exposed to untrusted sources that contain training data inserted by adversaries and bad actors. An adversary can insert a small number of poisoned samples, such as mislabeled samples from…

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a…

As the internet continues to be populated with new devices and emerging technologies, the attack surface grows exponentially. Technology is shifting towards a profit-driven Internet of Things market where security is an afterthought.…

Adversarial attacks have become a major threat for machine learning applications. There is a growing interest in studying these attacks in the audio domain, e.g, speech and speaker recognition; and find defenses against them. In this work,…

There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems. These attacks pose new challenges to deep learning security and have raised significant concerns in deploying ASR…

Recent work has shown the possibility of adversarial attacks on automatic speechrecognition (ASR) systems. However, in the vast majority of work in this area, theattacks have been executed only in the digital space, or have involved short…

Recent studies have highlighted audio adversarial examples as a ubiquitous threat to state-of-the-art automatic speech recognition systems. Thorough studies on how to effectively generate adversarial examples are essential to prevent…

Memory poisoning attacks for Agentic AI and multi-agent systems (MAS) have recently caught attention. It is partially due to the fact that Large Language Models (LLMs) facilitate the construction and deployment of agents. Different memory…

State-of-the-art machine learning models are vulnerable to data poisoning attacks whose purpose is to undermine the integrity of the model. However, the current literature on data poisoning attacks is mainly focused on ad hoc techniques…

There is an increasing interest in analyzing the behavior of machine learning systems against adversarial attacks. However, most of the research in adversarial machine learning has focused on studying weaknesses against evasion or poisoning…

Pretrained language models have significantly advanced performance across various natural language processing tasks. However, adversarial attacks continue to pose a critical challenge to systems built using these models, as they can be…

Machine learning is a powerful tool enabling full automation of a huge number of tasks without explicit programming. Despite recent progress of machine learning in different domains, these models have shown vulnerabilities when they are…

Deep learning has made significant breakthroughs in many fields, including electroencephalogram (EEG) based brain-computer interfaces (BCIs). However, deep learning models are vulnerable to adversarial attacks, in which deliberately…

Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoofing systems are critical for detecting such threats, prior…

Adversarial attacks, wherein slight inputs are carefully crafted to mislead intelligent models, have attracted increasing attention. However, a critical gap persists between theoretical advancements and practical application, particularly…