# Enhancing Targeted Adversarial Attacks on Large Vision-Language Models via Intermediate Projector

arXiv: https://arxiv.org/abs/2508.13739 · HTML: https://mlsanity.com/paper/2508.13739/

## Key facts

- Cited by 5 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 50 of its 70 references that are in the map.
- First posted on arXiv 19 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM jailbreaks and adversarial robustness](https://mlsanity.com/mllm/mllm-jailbreaks-and-adversarial-robustness/)
- 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, 30 of 50)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models](https://mlsanity.com/paper/2304.10592/) (2023)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [EVA-CLIP: Improved Training Techniques for CLIP at Scale](https://mlsanity.com/paper/2303.15389/) (2023)
- [DeepSeek-VL: Towards Real-World Vision-Language Understanding](https://mlsanity.com/paper/2403.05525/) (2024)
- [CogVLM: Visual Expert for Pretrained Language Models](https://mlsanity.com/paper/2311.03079/) (2023)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [On Evaluating Adversarial Robustness of Large Vision-Language Models](https://mlsanity.com/paper/2305.16934/) (2023)
- [A study of the effect of JPG compression on adversarial images](https://mlsanity.com/paper/1608.00853/) (2016)
- [A Self-supervised Approach for Adversarial Robustness](https://mlsanity.com/paper/2006.04924/) (2020)

## Built on by (most cited first, 5 of 5)

- [Adversarial attacks against Modern Vision-Language Models](https://mlsanity.com/paper/2603.16960/) (2026)
- [SGHA-Attack: Semantic-Guided Hierarchical Alignment for Transferable Targeted Attacks on Vision-Language Models](https://mlsanity.com/paper/2602.01574/) (2026)
- [AirflowAttack: Thermal-Airflow Adversarial Perturbations against Infrared Remote-Sensing Vision-Language Models](https://mlsanity.com/paper/2607.06485/) (2026)
- [It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at ε≤ 4/255](https://mlsanity.com/paper/2609.38298/) (2026)
- [Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models](https://mlsanity.com/paper/2609.39134/) (2026)

## Abstract (arXiv)

The growing deployment of Large Vision-Language Models (VLMs) raises safety concerns, as adversaries may exploit model vulnerabilities to induce harmful outputs, with targeted black-box adversarial attacks posing a particularly severe threat. However, existing methods primarily maximize encoder-level global similarity, which lacks the granularity for stealthy and practical fine-grained attacks, where only specific target should be altered (e.g., modifying a car while preserving its background). Moreover, they largely neglect the projector, a key semantic bridge in VLMs for multimodal alignment. To address these limitations, we propose a novel black-box targeted attack framework that leverages the projector. Specifically, we utilize the widely adopted Querying Transformer (Q-Former) which transforms global image embeddings into fine-grained query outputs, to enhance attack effectiveness and granularity. For standard global targeted attack scenarios, we propose the Intermediate Projector Guided Attack (IPGA), which aligns Q-Former fine-grained query outputs with the target to enhance attack strength and exploits the intermediate pretrained Q-Former that is not fine-tuned for any specific Large Language Model (LLM) to improve attack transferability. For fine-grained attack scenarios, we augment IPGA with the Residual Query Alignment (RQA) module, which preserves unrelated content by constraining non-target query outputs to enhance attack granularity. Extensive experiments demonstrate that IPGA significantly outperforms baselines in global targeted attacks, and IPGA with RQA (IPGA-R) attains superior success rates and unrelated content preservation over baselines in fine-grained attacks. Our method also transfers effectively to commercial VLMs such as Google Gemini and OpenAI GPT.