# Transferable Adversarial Attacks on SAM and Its Downstream Models

arXiv: https://arxiv.org/abs/2410.20197 · HTML: https://mlsanity.com/paper/2410.20197/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 55 of its 68 references that are in the map.
- First posted on arXiv 26 Oct 2024.

## Builds on (most cited first, 30 of 55)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [Adversarial examples in the physical world](https://mlsanity.com/paper/1607.02533/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [Universal adversarial perturbations](https://mlsanity.com/paper/1610.08401/) (2016)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Black-box Adversarial Attacks with Limited Queries and Information](https://mlsanity.com/paper/1804.08598/) (2018)
- [Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.12620/) (2023)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [Segment Anything in High Quality](https://mlsanity.com/paper/2306.01567/) (2023)
- [Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks](https://mlsanity.com/paper/1908.06281/) (2019)
- [HopSkipJumpAttack: A Query-Efficient Decision-Based Attack](https://mlsanity.com/paper/1904.02144/) (2019)
- [Segment Anything Model for Medical Image Analysis: an Experimental Study](https://mlsanity.com/paper/2304.10517/) (2023)
- [Customized Segment Anything Model for Medical Image Segmentation](https://mlsanity.com/paper/2304.13785/) (2023)
- [Enhancing the Transferability of Adversarial Attacks through Variance Tuning](https://mlsanity.com/paper/2103.15571/) (2021)
- [Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets](https://mlsanity.com/paper/2002.05990/) (2020)
- [Stacked Conditional Generative Adversarial Networks for Jointly Learning Shadow Detection and Shadow Removal](https://mlsanity.com/paper/1712.02478/) (2017)
- [Admix: Enhancing the Transferability of Adversarial Attacks](https://mlsanity.com/paper/2102.00436/) (2021)
- [Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priors](https://mlsanity.com/paper/1807.07978/) (2018)
- [Enhancing Adversarial Example Transferability with an Intermediate Level Attack](https://mlsanity.com/paper/1907.10823/) (2019)

## Built on by (most cited first, 21 of 21)

- [When Robots Obey the Patch: Universal Transferable Patch Attacks on Vision-Language-Action Models](https://mlsanity.com/paper/2511.21192/) (2025)
- [Backdoor Attacks against No-Reference Image Quality Assessment Models via a Scalable Trigger](https://mlsanity.com/paper/2412.07277/) (2024)
- [MTL-UE: Learning to Learn Nothing for Multi-Task Learning](https://mlsanity.com/paper/2505.05279/) (2025)
- [Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2](https://mlsanity.com/paper/2510.24195/) (2025)
- [Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation](https://mlsanity.com/paper/2504.14541/) (2025)
- [From Pretrain to Pain: Adversarial Vulnerability of Video Foundation Models Without Task Knowledge](https://mlsanity.com/paper/2511.07049/) (2025)
- [Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems](https://mlsanity.com/paper/2503.00383/) (2025)
- [ForensicsSAM: Toward Robust and Unified Image Forgery Detection and Localization Resisting to Adversarial Attack](https://mlsanity.com/paper/2508.07402/) (2025)
- [Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks](https://mlsanity.com/paper/2602.03284/) (2026)
- [AEGIS: Adversarial Target-Guided Retention-Data-Free Robust Concept Erasure from Diffusion Models](https://mlsanity.com/paper/2602.06771/) (2026)
- [Full spectrum Unlearnable Examples via Spectral Equalization](https://mlsanity.com/paper/2606.26719/) (2026)
- [Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models](https://mlsanity.com/paper/2604.22552/) (2026)
- [Creating Blank Canvas Against AI-enabled Image Forgery](https://mlsanity.com/paper/2511.22237/) (2025)
- [Universal Adversarial Attacks against Closed-Source MLLMs via Target-View Routed Meta Optimization](https://mlsanity.com/paper/2601.23179/) (2026)
- [Keep It Real: Challenges in Attacking Compression-Based Adversarial Purification](https://mlsanity.com/paper/2508.05489/) (2025)
- [SAM Encoder Breach by Adversarial Simplicial Complex Triggers Downstream Model Failures](https://mlsanity.com/paper/2508.06127/) (2025)
- [Malicious Image Analysis via Vision-Language Segmentation Fusion: Detection, Element, and Location in One-shot](https://mlsanity.com/paper/2512.04599/) (2025)
- [Feature-Space Smoothing: Certified Robustness of Deep Representations](https://mlsanity.com/paper/2601.16200/) (2026)
- [Universal Concept Disruption for SAM3 Image Segmentation](https://mlsanity.com/paper/2608.05983/) (2026)
- [Universal Cross-Prompt Adversarial Attacks on Promptable Concept Segmentation](https://mlsanity.com/paper/2609.39265/) (2026)
- [Across Viewpoints and Time: Trajectory-Generalizable Physical Attacks on World Models and Video Understanding Models](https://mlsanity.com/paper/2610.15343/) (2026)

## Abstract (arXiv)

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility also poses threats of adverse usage. This paper, for the first time, explores the feasibility of adversarial attacking various downstream models fine-tuned from the segment anything model (SAM), by solely utilizing the information from the open-sourced SAM. In contrast to prevailing transfer-based adversarial attacks, we demonstrate the existence of adversarial dangers even without accessing the downstream task and dataset to train a similar surrogate model. To enhance the effectiveness of the adversarial attack towards models fine-tuned on unknown datasets, we propose a universal meta-initialization (UMI) algorithm to extract the intrinsic vulnerability inherent in the foundation model, which is then utilized as the prior knowledge to guide the generation of adversarial perturbations. Moreover, by formulating the gradient difference in the attacking process between the open-sourced SAM and its fine-tuned downstream models, we theoretically demonstrate that a deviation occurs in the adversarial update direction by directly maximizing the distance of encoded feature embeddings in the open-sourced SAM. Consequently, we propose a gradient robust loss that simulates the associated uncertainty with gradient-based noise augmentation to enhance the robustness of generated adversarial examples (AEs) towards this deviation, thus improving the transferability. Extensive experiments demonstrate the effectiveness of the proposed universal meta-initialized and gradient robust adversarial attack (UMI-GRAT) toward SAMs and their downstream models. Code is available at https://github.com/xiasong0501/GRAT.