# SEA: Low-Resource Safety Alignment for Multimodal Large Language Models via Synthetic Embeddings

arXiv: https://arxiv.org/abs/2502.12562 · HTML: https://mlsanity.com/paper/2502.12562/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in MLLM jailbreaks and adversarial robustness, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- LLM alignment / RLHF / preference optimisation / [Safety alignment and jailbreak attacks](https://mlsanity.com/alignment/safety-alignment-and-jailbreak-attacks/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 23 of 23)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Universal and Transferable Adversarial Attacks on Aligned Language Models](https://mlsanity.com/paper/2307.15043/) (2023)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis](https://mlsanity.com/paper/2405.21075/) (2024)
- [MVBench: A Comprehensive Multi-modal Video Understanding Benchmark](https://mlsanity.com/paper/2311.17005/) (2023)
- [VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs](https://mlsanity.com/paper/2406.07476/) (2024)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://mlsanity.com/paper/2406.15513/) (2024)
- [JailBreakV: A Benchmark for Assessing the Robustness of MultiModal Large Language Models against Jailbreak Attacks](https://mlsanity.com/paper/2404.03027/) (2024)
- [AIR-Bench: Benchmarking Large Audio-Language Models via Generative Comprehension](https://mlsanity.com/paper/2402.07729/) (2024)
- [DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback](https://mlsanity.com/paper/2311.10081/) (2023)
- [SPA-VL: A Comprehensive Safety Preference Alignment Dataset for Vision Language Model](https://mlsanity.com/paper/2406.12030/) (2024)
- [VLSBench: Unveiling Visual Leakage in Multimodal Safety](https://mlsanity.com/paper/2411.19939/) (2024)
- [Align Anything: Training All-Modality Models to Follow Instructions with Language Feedback](https://mlsanity.com/paper/2412.15838/) (2024)
- [Assessment of Multimodal Large Language Models in Alignment with Human Values](https://mlsanity.com/paper/2403.17830/) (2024)
- [Cross-Modal Safety Alignment: Is textual unlearning all you need?](https://mlsanity.com/paper/2406.02575/) (2024)

## Built on by (most cited first, 11 of 11)

- [Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models](https://mlsanity.com/paper/2508.07173/) (2025)
- [Rethinking Jailbreak Detection of Large Vision Language Models with Representational Contrastive Scoring](https://mlsanity.com/paper/2512.12069/) (2025)
- [ARGUS: Defending Against Multimodal Indirect Prompt Injection via Steering Instruction-Following Behavior](https://mlsanity.com/paper/2512.05745/) (2025)
- [Harmonious Parameter Adaptation in Continual Visual Instruction Tuning for Safety-Aligned MLLMs](https://mlsanity.com/paper/2511.20158/) (2025)
- [Empowering Multimodal LLMs with External Tools: A Comprehensive Survey](https://mlsanity.com/paper/2508.10955/) (2025)
- [Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction](https://mlsanity.com/paper/2605.18104/) (2026)
- [Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware Evaluation](https://mlsanity.com/paper/2605.30031/) (2026)
- [AEGIS: Audio Endogenous Guarding via Internal Signals Against Large Audio-Language Model Jailbreaks](https://mlsanity.com/paper/2609.29287/) (2026)
- [StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs](https://mlsanity.com/paper/2605.25534/) (2026)
- [V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure](https://mlsanity.com/paper/2607.21151/) (2026)
- [Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization](https://mlsanity.com/paper/2610.02019/) (2026)

## Abstract (arXiv)

Multimodal Large Language Models (MLLMs) have serious security vulnerabilities.While safety alignment using multimodal datasets consisting of text and data of additional modalities can effectively enhance MLLM's security, it is costly to construct these datasets. Existing low-resource security alignment methods, including textual alignment, have been found to struggle with the security risks posed by additional modalities. To address this, we propose Synthetic Embedding augmented safety Alignment (SEA), which optimizes embeddings of additional modality through gradient updates to expand textual datasets. This enables multimodal safety alignment training even when only textual data is available. Extensive experiments on image, video, and audio-based MLLMs demonstrate that SEA can synthesize a high-quality embedding on a single RTX3090 GPU within 24 seconds. SEA significantly improves the security of MLLMs when faced with threats from additional modalities. To assess the security risks introduced by video and audio, we also introduced a new benchmark called VA-SafetyBench. High attack success rates across multiple MLLMs validate its challenge. Our code and data will be available at https://github.com/ZeroNLP/SEA.