This paper provides a unified taxonomy and controlled empirical evaluation of jailbreak attacks and defenses for Large Audio Language Models (LALMs), demonstrating that safety evaluation must consider…

The paper introduces Acoustic Interference Attack (AIA), a novel jailbreak method that bypasses Large Audio Language Model (LALM) safety alignments by manipulating the underlying acoustic latent seman…

The paper introduces Token-Aware Gradient Optimization (TAGO), demonstrating that sparse optimization focusing only on high-gradient audio tokens is sufficient for effective jailbreaking of audio lang…

The paper introduces a novel Clean-Referenced Feature-Vocoder Attack, a black-box adversarial attack that perturbs high-level SSL feature representations instead of raw audio waveforms, achieving supe…

This survey provides a comprehensive taxonomy and vulnerability-centric analysis of adversarial attacks targeting Multimodal Large Language Models (MLLMs), offering an explanatory framework for enhanc…

The paper introduces MARS, a novel meta-adversarial framework that significantly improves black-box adversarial attacks against state-of-the-art Singing Voice Deepfake Detection (SVDD) systems by esca…

AttackEval systematically evaluates the effectiveness of 250 prompt injection prompts across ten attack categories, finding that composite and obfuscation attacks are highly effective against current…

The paper introduces Multi-Clip Video (MCV) SafetyBench, a dataset demonstrating that the vulnerability of Multimodal Large Language Models (MLLMs) to jailbreaking increases with the diversity and num…

The paper introduces 'log-substrate prompt injection,' demonstrating that attacker-controlled log fields can be used to manipulate LLM-powered security analysis, with persona hijacking and context man…

The paper introduces Transient Turn Injection (TTI), a novel multi-turn attack technique that exploits stateless moderation in LLMs by distributing adversarial intent across isolated interactions, rev…

This paper demonstrates that benign fine-tuning significantly degrades safety in Audio LLMs, showing that the vulnerability is distinct from text and vision modalities and is highly dependent on the m…

The paper introduces Tree structured Injection for Payloads (TIP), a novel black-box attack framework that reliably generates stealthy injection payloads to seize control of LLM agents utilizing the M…

The paper proposes a novel cross-modal backdoor attack that exploits the vulnerability of lightweight connectors in multimodal LLMs, demonstrating high attack success rates across different modalities…