cs.LGJan 30, 2026

The Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer

Authors: Yupeng Chen, Junchi Yu, Aoxi Liu, Baoyuan Wu, Philip Torr, Adel Bibi

Organizations: Torr Vision Group, University of Oxford · The Chinese University of Hong Kong, Shenzhen

Abstract

Recent advances in end-to-end trained omni-models have substantially improved audio capabilities by strengthening text-audio modality alignment. However, whether such alignment inadvertently facilitates the transfer of safety vulnerabilities across modalities remains underexplored. This question is critical as text-based jailbreak attacks are considerably more mature than audio-based ones; if they transfer systematically, current audio safety evaluations may underestimate risks originating from the text modality. In this paper, we introduce the Alignment Curse, a formally characterized and empirically validated principle showing that stronger modality alignment enables more effective transfer of attacks from text to audio, revealing a fundamental tension between capability and safety. Motivated by this principle, we conduct a comprehensive black-box evaluation of three attack categories on recent omni-models (e.g., Qwen2.5-Omni, Qwen3-Omni): text attacks, text-transferred audio attacks, and audio attacks. We find that text-transferred audio attacks perform comparably to, and often better than, audio-based attacks, exhibiting a clear advantage under audio-only access. This suggests that text-based vulnerabilities play a pivotal role in shaping audio safety risks. Finally, we empirically analyze the relationship between modality alignment and transfer effectiveness across attack methods and models, observing consistent support for the Alignment Curse: tighter modality alignment leads to more effective cross-modality attack transfer.

Figures & tables

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 17, 2026

Benign Fine-Tuning Breaks Safety Alignment in Audio LLMs

Fine-tuning on benign data is known to degrade safety alignment in text and vision LLMs, but whether distinct input properties drive this vulnerability differently remains unclear. Audio introduces a richer problem where benign samples can neighbor harmful content through what is said or how it sounds. We present the first systematic study of benign fine-tuning safety in Audio LLMs, evaluating three state-of-the-art models with a proximity-based framework that decomposes embedding-space distance into semantic, acoustic, and mixed axes. We find that the dominant vulnerability axis is architecture-conditioned, determined by how each model's encoder and projector transform audio into the backbone LLM's input space. Across three models, benign fine-tuning elevates Jailbreak Success Rate (JSR) from single digits to as high as 87%, with the most damaging axis shifting from semantic to acoustic proximity depending on encoder design. Mechanistically, fine-tuning selectively suppresses late-layer refusal circuits while frozen encoders preserve upstream representations: the model still detects harmful content but stops refusing, a recognition-refusal dissociation. Two practical defenses, filtering training data to maximize distance from harmful embeddings and a textual system prompt at inference, reduce JSR to near-zero without architectural modification. These findings show that safety evaluation should account for modality and architecture, while highlighting Audio LLMs as a useful testbed for understanding alignment fragility.
Mar 19, 2026

On Optimizing Multimodal Jailbreaks for Spoken Language Models

As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone while introducing an expanded attack surface. SLMs have been previously shown to be susceptible to jailbreaking, where adversarial prompts induce harmful responses. Yet existing attacks largely remain unimodal, optimizing either text or audio in isolation. We explore gradient-based multimodal jailbreaks by introducing JAMA (Joint Audio-text Multimodal Attack), a joint multimodal optimization framework combining Greedy Coordinate Gradient (GCG) for text and Projected Gradient Descent (PGD) for audio, to simultaneously perturb both modalities. Evaluations across four state-of-the-art SLMs and four audio types demonstrate that JAMA surpasses unimodal jailbreak rate by 1.5x to 20x. We analyze the operational dynamics of this joint attack and show that a sequential approximation method makes it 4x to 6x faster. Our findings suggest that unimodal safety is insufficient for robust SLMs. The code and data are available at https://repos.lsv.uni-saarland.de/akrishnan/multimodal-jailbreak-slm.
Apr 5, 2026

A Systematic Study of Cross-Modal Typographic Attacks on Audio-Visual Reasoning

As audio-visual multi-modal large language models (MLLMs) are increasingly deployed in safety-critical applications, understanding their cross-modal vulnerabilities is essential. To this end, we introduce Multi-Modal Typography, a systematic study examining how perturbations added to speech and on-screen text impact audio-visual reasoning of closed- and open-source models. For instance, on the WorldSense benchmark, the attack success rate (ASR) against Gemini 3.7 Flash increased from 9.53% to 43.41%, highlighting its vulnerability. We analyze the cross-modal effects of unimodal and multimodal attacks and evaluate how specific properties of the attacks impact the overall multi-modal reasoning. By applying fine-tuning as a mitigation, we lower the ASR of Qwen2.5-Omni-7B on WorldSense from 60.6%60.6\% to 52.0%52.0\%. Our findings across multi-modal reasoning tasks, content moderation, and offline robot task selection benchmarks establish multi-modal typography as a critical and underexplored attack strategy in multi-modal reasoning. Code and data will be made publicly available.