# Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models

arXiv: https://arxiv.org/abs/2509.19994 · HTML: https://mlsanity.com/paper/2509.19994/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 83 of its 104 references that are in the map.
- First posted on arXiv 24 Sep 2025.

## Builds on (most cited first, 30 of 83)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [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)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs](https://mlsanity.com/paper/2111.02114/) (2021)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [CoCa: Contrastive Captioners are Image-Text Foundation Models](https://mlsanity.com/paper/2205.01917/) (2022)
- [ImageBind: One Embedding Space To Bind Them All](https://mlsanity.com/paper/2305.05665/) (2023)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning](https://mlsanity.com/paper/2203.02053/) (2022)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [BERT-ATTACK: Adversarial Attack Against BERT Using BERT](https://mlsanity.com/paper/2004.09984/) (2020)
- [Diffusion Models for Adversarial Purification](https://mlsanity.com/paper/2205.07460/) (2022)
- [SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks](https://mlsanity.com/paper/2310.03684/) (2023)
- [Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks](https://mlsanity.com/paper/1904.02884/) (2019)
- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)

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

- [ContextNav: Towards Agentic Multimodal In-Context Learning](https://mlsanity.com/paper/2510.04560/) (2025)
- [VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG](https://mlsanity.com/paper/2604.05418/) (2026)
- [Test-Time Attention Purification for Backdoored Large Vision Language Models](https://mlsanity.com/paper/2603.12989/) (2026)
- [CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning](https://mlsanity.com/paper/2605.29602/) (2026)
- [V-DEAL: Diagnosing Video Safety De-Calibration as an Understanding-Refusal Coupling Failure](https://mlsanity.com/paper/2607.21151/) (2026)

## Abstract (arXiv)

Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success across downstream tasks. However, their increasing adoption raises serious security concerns, especially regarding targeted adversarial attacks. In this paper, we show that existing targeted adversarial attacks on multimodal pre-trained models still have limitations in two aspects: generalizability and undetectability. Specifically, the crafted targeted adversarial examples (AEs) exhibit limited generalization to partially known or semantically similar targets in cross-modal alignment tasks (i.e., limited generalizability) and can be easily detected by simple anomaly detection methods (i.e., limited undetectability). To address these limitations, we propose a novel method called Proxy Targeted Attack (PTA), which leverages multiple source-modal and target-modal proxies to optimize targeted AEs, ensuring they remain evasive to defenses while aligning with multiple potential targets. We also provide theoretical analyses to highlight the relationship between generalizability and undetectability and to ensure optimal generalizability while meeting the specified requirements for undetectability. Furthermore, experimental results demonstrate that our PTA can achieve a high success rate across various related targets and remain undetectable against multiple anomaly detection methods.