# Tit-for-Tat: Safeguarding Large Vision-Language Models Against Jailbreak Attacks via Adversarial Defense

arXiv: https://arxiv.org/abs/2503.11619 · HTML: https://mlsanity.com/paper/2503.11619/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Vision-language and text-to-image safety, one of 12 directions in LLM safety and security.
- Builds on 26 of its 39 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Placed in

- 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, 26 of 26)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Jailbreaking Black Box Large Language Models in Twenty Queries](https://mlsanity.com/paper/2310.08419/) (2023)
- [MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities](https://mlsanity.com/paper/2308.02490/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts](https://mlsanity.com/paper/2311.05608/) (2023)
- [Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models](https://mlsanity.com/paper/2307.14539/) (2023)
- [How Robust is Google's Bard to Adversarial Image Attacks?](https://mlsanity.com/paper/2309.11751/) (2023)
- [Defending Large Language Models Against Jailbreaking Attacks Through Goal Prioritization](https://mlsanity.com/paper/2311.09096/) (2023)
- [Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models](https://mlsanity.com/paper/2403.09792/) (2024)
- [DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models](https://mlsanity.com/paper/2310.16436/) (2023)
- [AdaShield: Safeguarding Multimodal Large Language Models from Structure-based Attack via Adaptive Shield Prompting](https://mlsanity.com/paper/2403.09513/) (2024)
- [Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation](https://mlsanity.com/paper/2403.09572/) (2024)
- [MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance](https://mlsanity.com/paper/2401.02906/) (2024)
- [How Many Unicorns Are in This Image? A Safety Evaluation Benchmark for Vision LLMs](https://mlsanity.com/paper/2311.16101/) (2023)
- [Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt](https://mlsanity.com/paper/2406.04031/) (2024)
- [Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLP](https://mlsanity.com/paper/2210.10683/) (2022)
- [DRESS: Instructing Large Vision-Language Models to Align and Interact with Humans via Natural Language Feedback](https://mlsanity.com/paper/2311.10081/) (2023)
- [Jailbreaking GPT-4V via Self-Adversarial Attacks with System Prompts](https://mlsanity.com/paper/2311.09127/) (2023)
- [ImgTrojan: Jailbreaking Vision-Language Models with ONE Image](https://mlsanity.com/paper/2403.02910/) (2024)
- [Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency](https://mlsanity.com/paper/2501.04931/) (2025)
- [Efficient Generation of Targeted and Transferable Adversarial Examples for Vision-Language Models Via Diffusion Models](https://mlsanity.com/paper/2404.10335/) (2024)
- [Constructing Semantics-Aware Adversarial Examples with a Probabilistic Perspective](https://mlsanity.com/paper/2306.00353/) (2023)

## Built on by (most cited first, 2 of 2)

- [DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt](https://mlsanity.com/paper/2506.09353/) (2025)
- [SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning](https://mlsanity.com/paper/2608.10513/) (2026)

## Abstract (arXiv)

Deploying large vision-language models (LVLMs) introduces a unique vulnerability: susceptibility to malicious attacks via visual inputs. However, existing defense methods suffer from two key limitations: (1) They solely focus on textual defenses, fail to directly address threats in the visual domain where attacks originate, and (2) the additional processing steps often incur significant computational overhead or compromise model performance on benign tasks. Building on these insights, we propose ESIII (Embedding Security Instructions Into Images), a novel methodology for transforming the visual space from a source of vulnerability into an active defense mechanism. Initially, we embed security instructions into defensive images through gradient-based optimization, obtaining security instructions in the visual dimension. Subsequently, we integrate security instructions from visual and textual dimensions with the input query. The collaboration between security instructions from different dimensions ensures comprehensive security protection. Extensive experiments demonstrate that our approach effectively fortifies the robustness of LVLMs against such attacks while preserving their performance on standard benign tasks and incurring an imperceptible increase in time costs.