paper-with-me

홈 › Papers

Task-Agnostic Attacks Against Vision Foundation Models

2025-03-05 · Brian Pulfer, Yury Belousov, Vitaliy Kinakh, Teddy Furon, Slava Voloshynovskiy

The study of security in machine learning mainly focuses on downstream task-specific attacks, where the adversarial example is obtained by optimizing a loss function specific to the downstream task. At the same time, it has become standard practice for machine learning practitioners to adopt publicly available pre-trained vision foundation models, effectively sharing a common backbone architecture across a multitude of applications such as classification, segmentation, depth estimation, retrieval, question-answering and more. The study of attacks on such foundation models and their impact to multiple downstream tasks remains vastly unexplored. This work proposes a general framework that forges task-agnostic adversarial examples by maximally disrupting the feature representation obtained with foundation models. We extensively evaluate the security of the feature representations obtained by popular vision foundation models by measuring the impact of this attack on multiple downstream tasks and its transferability between models.

📄 PDF Abstract BibTeX arXiv:2503.03842

Code (1)

BrianPulfer/fsaa 공식 구현 pytorch

Tasks

Depth EstimationQuestion Answering

Methods 이 논문이 사용한 방법론

ADOPT Please enter a description about the method here

Similar Papers 제목 키워드 기반

TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models

2024-05-27 · Yuzhou. Nie, Yanting. Wang, Jinyuan. Jia, Michael J. De Lucia 외

One key challenge in backdoor attacks against large foundation models is the resource limits. Backdoor attacks usually require retraining the target model, which is impractical for very large foundation models. Existing …

Backdoor AttackGPU

Attacking Attention of Foundation Models Disrupts Downstream Tasks

2025-06-03 · Hondamunige Prasanna Silva, Federico Becattini, Lorenzo Seidenari

Foundation models represent the most prominent and recent paradigm shift in artificial intelligence. Foundation models are large models, trained on broad data that deliver high accuracy in many downstream tasks, often wi…

Depth EstimationImage-text RetrievalText Retrieval

Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography

2024-05-23 · Nhat Chung, Sensen Gao, Tuan-Anh Vu, Jie Zhang 외

Vision-Large-Language-Models (Vision-LLMs) are increasingly being integrated into autonomous driving (AD) systems due to their advanced visual-language reasoning capabilities, targeting the perception, prediction, planni…

Autonomous DrivingDecision Making

Adversarial Attacks on Foundational Vision Models

2023-08-28 · Nathan Inkawhich, Gwendolyn McDonald, Ryan Luley

Rapid progress is being made in developing large, pretrained, task-agnostic foundational vision models such as CLIP, ALIGN, DINOv2, etc. In fact, we are approaching the point where these models do not have to be finetune…

BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models

2021-10-06 · ICLR 2022 4 · Kangjie Chen, Yuxian Meng, Xiaofei Sun, Shangwei Guo 외

Pre-trained Natural Language Processing (NLP) models can be easily adapted to a variety of downstream language tasks. This significantly accelerates the development of language models. However, NLP models have been shown…

Backdoor AttackTransfer Learning