mlsanityData to 7 Oct 2026

BadSAM: Exploring Security Vulnerabilities of SAM via Backdoor Attacks

arXiv 2305.03289 ↗First posted 5 May 2023cs.CV cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Recently, the Segment Anything Model (SAM) has gained significant attention as an image segmentation foundation model due to its strong performance on various downstream tasks. However, it has been found that SAM does not always perform satisfactorily when faced with challenging downstream tasks. This has led downstream users to demand a customized SAM model that can be adapted to these downstream tasks. In this paper, we present BadSAM, the first backdoor attack on the image segmentation foundation model. Our preliminary experiments on the CAMO dataset demonstrate the effectiveness of BadSAM.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 8 of its 9 references that are in the map. First posted on arXiv 5 May 2023.

Builds on

8 of 9 references.

References · 8

  1. 2023Segment Anythingcited by 8,158
  2. 2021Anabranch Network for Camouflaged Object Segmentationcited by 227
  3. 2023Segment Anything Model (SAM) for Digital Pathology: Assess Zero-shot Segmentation on Whole Slide Imagingcited by 161
  4. 2023Can SAM Segment Anything? When SAM Meets Camouflaged Object Detectioncited by 99
  5. 2023Text2Seg: Remote Sensing Image Semantic Segmentation via Text-Guided Visual Foundation Modelscited by 44
  6. 2021Hidden Backdoor Attack against Semantic Segmentation Modelscited by 19
  7. 2023Influencer Backdoor Attack on Semantic Segmentationcited by 5
  8. 2023Backdoor Attacks to Pre-trained Unified Foundation Modelscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 3.

7 papers.

  1. 2023A Comprehensive Survey on Segment Anything Model for Vision and Beyondcited by 64
  2. 2023Artificial General Intelligence for Medical Imaging Analysiscited by 32
  3. 2023SAM-PARSER: Fine-tuning SAM Efficiently by Parameter Space Reconstructioncited by 23
  4. 2024SAM as the Guide: Mastering Pseudo-Label Refinement in Semi-Supervised Referring Expression Segmentationcited by 17
  5. 2023Task-Driven Causal Feature Distillation: Towards Trustworthy Risk Predictioncited by 9
  6. 2024BadCLM: Backdoor Attack in Clinical Language Models for Electronic Health Recordscited by 5
  7. 2024TETRIS: Towards Exploring the Robustness of Interactive Segmentationcited by 2