English
Related papers

Related papers: When Good Sounds Go Adversarial: Jailbreaking Audi…

200 papers

An adversarial attack is an exploitative process in which minute alterations are made to natural inputs, causing the inputs to be misclassified by neural models. In the field of speech recognition, this has become an issue of increasing…

Sound · Computer Science 2018-09-13 Krishan Rajaratnam , Kunal Shah , Jugal Kalita

Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…

Cryptography and Security · Computer Science 2025-11-24 Yige Li , Zhe Li , Wei Zhao , Nay Myat Min , Hanxun Huang , Xingjun Ma , Jun Sun

In a transfer-based attack against Automatic Speech Recognition (ASR) systems, attacks are unable to access the architecture and parameters of the target model. Existing attack methods are mostly investigated in voice assistant scenarios…

Sound · Computer Science 2023-03-29 Qi Gege , Yuefeng Chen , Xiaofeng Mao , Yao Zhu , Binyuan Hui , Xiaodan Li , Rong Zhang , Hui Xue

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…

Sound · Computer Science 2021-03-16 Mohammad Esmaeilpour , Patrick Cardinal , Alessandro Lameiras Koerich

Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these…

Sound · Computer Science 2022-02-18 Mia Chiquier , Chengzhi Mao , Carl Vondrick

Large Multimodal Models (LMMs) have demonstrated the ability to interact with humans under real-world conditions by combining Large Language Models (LLMs) and modality encoders to align multimodal information (visual and auditory) with…

Computation and Language · Computer Science 2024-11-01 Hao Yang , Lizhen Qu , Ehsan Shareghi , Gholamreza Haffari

Speech Language Models (SLMs) enable natural interactions via spoken instructions, which more effectively capture user intent by detecting nuances in speech. The richer speech signal introduces new security risks compared to text-based…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-17 Amirbek Djanibekov , Nurdaulet Mukhituly , Kentaro Inui , Hanan Aldarmaki , Nils Lukas

We propose a method to generate audio adversarial examples that can attack a state-of-the-art speech recognition model in the physical world. Previous work assumes that generated adversarial examples are directly fed to the recognition…

Machine Learning · Computer Science 2019-08-20 Hiromu Yakura , Jun Sakuma

As Audio Large Language Models (ALLMs) emerge as powerful tools for speech processing, their safety implications demand urgent attention. While considerable research has explored textual and vision safety, audio's distinct characteristics…

Large Language Models (LLMs) are susceptible to Jailbreaking attacks, which aim to extract harmful information by subtly modifying the attack query. As defense mechanisms evolve, directly obtaining harmful information becomes increasingly…

Machine Learning · Computer Science 2024-10-03 Yixin Cheng , Markos Georgopoulos , Volkan Cevher , Grigorios G. Chrysos

Safety backdoor attacks in large language models (LLMs) enable the stealthy triggering of unsafe behaviors while evading detection during normal interactions. The high dimensionality of potential triggers in the token space and the diverse…

Cryptography and Security · Computer Science 2024-06-26 Yi Zeng , Weiyu Sun , Tran Ngoc Huynh , Dawn Song , Bo Li , Ruoxi Jia

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Machine Learning · Computer Science 2024-10-28 Samuel Jacob Chacko , Sajib Biswas , Chashi Mahiul Islam , Fatema Tabassum Liza , Xiuwen Liu

Large Language Models (LLMs) have achieved impressive performance across diverse natural language processing tasks, but their growing power also amplifies potential risks such as jailbreak attacks that circumvent built-in safety mechanisms.…

Artificial Intelligence · Computer Science 2025-10-01 Qinjian Zhao , Jiaqi Wang , Zhiqiang Gao , Zhihao Dou , Belal Abuhaija , Kaizhu Huang

The proliferation of open-weight Large Language Models (LLMs) has democratized agentic AI, yet fine-tuned weights are frequently shared and adopted with limited scrutiny beyond leaderboard performance. This creates a risk where third-party…

Cryptography and Security · Computer Science 2026-03-05 Bhanu Pallakonda , Mikkel Hindsbo , Sina Ehsani , Prag Mishra

Large language models (LLMs) have demonstrated significant utility in a wide range of applications; however, their deployment is plagued by security vulnerabilities, notably jailbreak attacks. These attacks manipulate LLMs to generate…

Computation and Language · Computer Science 2025-03-12 Wenlong Meng , Fan Zhang , Wendao Yao , Zhenyuan Guo , Yuwei Li , Chengkun Wei , Wenzhi Chen

Adversarial attacks pose a threat to deep learning models. However, research on adversarial detection methods, especially in the multi-modal domain, is very limited. In this work, we propose an efficient and straightforward detection method…

Computer Vision and Pattern Recognition · Computer Science 2021-02-15 Pingchuan Ma , Stavros Petridis , Maja Pantic

Despite their immense popularity, deep learning-based acoustic systems are inherently vulnerable to adversarial attacks, wherein maliciously crafted audios trigger target systems to misbehave. In this paper, we present SirenAttack, a new…

Cryptography and Security · Computer Science 2019-07-25 Tianyu Du , Shouling Ji , Jinfeng Li , Qinchen Gu , Ting Wang , Raheem Beyah

We demonstrate the existence of universal adversarial perturbations, which can fool a family of audio classification architectures, for both targeted and untargeted attack scenarios. We propose two methods for finding such perturbations.…

Machine Learning · Computer Science 2020-11-18 Sajjad Abdoli , Luiz G. Hafemann , Jerome Rony , Ismail Ben Ayed , Patrick Cardinal , Alessandro L. Koerich

Large Language Model (LLM) jailbreak refers to a type of attack aimed to bypass the safeguard of an LLM to generate contents that are inconsistent with the safe usage guidelines. Based on the insights from the self-attention computation…

Cryptography and Security · Computer Science 2025-02-10 Zhilong Wang , Haizhou Wang , Nanqing Luo , Lan Zhang , Xiaoyan Sun , Yebo Cao , Peng Liu

Iterative jailbreak methods that repeatedly rewrite and input prompts into large language models (LLMs) to induce harmful outputs -- using the model's previous responses to guide each new iteration -- have been found to be a highly…

Computation and Language · Computer Science 2025-10-21 Masahiro Kaneko , Zeerak Talat , Timothy Baldwin