Copertina

Breaking Audio Large Language Models by Attacking Only the Encoder: A Universal Targeted Latent-Space Audio Attack

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ziv, Roee, Lapid, Raz, Sipper, Moshe
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Sound Artificial Intelligence Cryptography and Security
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models
di: Chen, Guangke, et al.
Pubblicazione: (2025)

AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models
di: Kang, Mintong, et al.
Pubblicazione: (2024)

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection
di: Chen, Meng, et al.
Pubblicazione: (2026)

XAI-Based Detection of Adversarial Attacks on Deepfake Detectors
di: Pinhasov, Ben, et al.
Pubblicazione: (2024)

Measuring the Robustness of Audio Deepfake Detectors
di: Li, Xiang, et al.
Pubblicazione: (2025)

On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspective
di: Alter, Tal, et al.
Pubblicazione: (2024)

ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features
di: Cheng, Peng, et al.
Pubblicazione: (2024)

Exploring Audio Editing Features as User-Centric Privacy Defenses Against Large Language Model(LLM) Based Emotion Inference Attacks
di: Soumik, Mohd. Farhan Israk, et al.
Pubblicazione: (2025)

JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models
di: Peng, Zifan, et al.
Pubblicazione: (2025)

Acoustic Interference: A New Paradigm Weaponizing Acoustic Latent Semantic for Universal Jailbreak against Large Audio Language Models
di: Wang, Yanyun, et al.
Pubblicazione: (2026)

Decoding Deception: Understanding Automatic Speech Recognition Vulnerabilities in Evasion and Poisoning Attacks
di: G, Aravindhan, et al.
Pubblicazione: (2025)

When Good Sounds Go Adversarial: Jailbreaking Audio-Language Models with Benign Inputs
di: Dingeto, Hiskias, et al.
Pubblicazione: (2025)

Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
di: Liu, Chang, et al.
Pubblicazione: (2025)

Now You Hear Me: Audio Narrative Attacks Against Large Audio-Language Models
di: Yu, Ye, et al.
Pubblicazione: (2026)

SyncGuard: Robust Audio Watermarking Capable of Countering Desynchronization Attacks
di: Gan, Zhenliang, et al.
Pubblicazione: (2025)

GROOT: Generating Robust Watermark for Diffusion-Model-Based Audio Synthesis
di: Liu, Weizhi, et al.
Pubblicazione: (2024)

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs
di: Roh, Jaechul, et al.
Pubblicazione: (2026)

Synthetic Voices, Real Threats: Evaluating Large Text-to-Speech Models in Generating Harmful Audio
di: Chen, Guangke, et al.
Pubblicazione: (2025)

DeePen: Penetration Testing for Audio Deepfake Detection
di: Müller, Nicolas, et al.
Pubblicazione: (2025)

Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
di: Fang, Zheng, et al.
Pubblicazione: (2026)

SARSteer: Safeguarding Large Audio-Language Models via Safe-Ablated Refusal Steering
di: Lin, Weilin, et al.
Pubblicazione: (2025)

Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectors
di: Lapid, Raz, et al.
Pubblicazione: (2023)

Yours or Mine? Overwriting Attacks Against Neural Audio Watermarking
di: Yao, Lingfeng, et al.
Pubblicazione: (2025)

Attacker's Noise Can Manipulate Your Audio-based LLM in the Real World
di: Sadasivan, Vinu Sankar, et al.
Pubblicazione: (2025)

STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling
di: Wang, Kun, et al.
Pubblicazione: (2026)

SafeEar: Content Privacy-Preserving Audio Deepfake Detection
di: Li, Xinfeng, et al.
Pubblicazione: (2024)

Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset
di: Oiso, Hideyuki, et al.
Pubblicazione: (2024)

Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
di: Yao, Lingfeng, et al.
Pubblicazione: (2026)

Multilingual and Multi-Accent Jailbreaking of Audio LLMs
di: Roh, Jaechul, et al.
Pubblicazione: (2025)

FlowMur: A Stealthy and Practical Audio Backdoor Attack with Limited Knowledge
di: Lan, Jiahe, et al.
Pubblicazione: (2023)

Rehearsal with Auxiliary-Informed Sampling for Audio Deepfake Detection
di: Febrinanto, Falih Gozi, et al.
Pubblicazione: (2025)

Smark: A Watermark for Text-to-Speech Diffusion Models via Discrete Wavelet Transform
di: Zhang, Yichuan, et al.
Pubblicazione: (2025)

XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
di: Liu, Yixin, et al.
Pubblicazione: (2025)

A Survey of Attacks on Large Language Models
di: Xu, Wenrui, et al.
Pubblicazione: (2025)

A Comprehensive Real-World Assessment of Audio Watermarking Algorithms: Will They Survive Neural Codecs?
di: Özer, Yigitcan, et al.
Pubblicazione: (2025)

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models
di: Park, Junyoung, et al.
Pubblicazione: (2026)

SCDF: A Speaker Characteristics DeepFake Speech Dataset for Bias Analysis
di: Staněk, Vojtěch, et al.
Pubblicazione: (2025)

SOLIDO: A Robust Watermarking Method for Speech Synthesis via Low-Rank Adaptation
di: Li, Yue, et al.
Pubblicazione: (2025)

Beyond Content: A Comprehensive Speech Toxicity Dataset and Detection Framework Incorporating Paralinguistic Cues
di: Ba, Zhongjie, et al.
Pubblicazione: (2026)

Align is not Enough: Multimodal Universal Jailbreak Attack against Multimodal Large Language Models
di: Wang, Youze, et al.
Pubblicazione: (2025)