Adversarial Attacks on Foundational Vision Models
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 finetuned downstream, and can simply be used in zero-shot or with a lightweight probing head. Critically, given the complexity of working at this scale, there is a bottleneck where relatively few organizations in the world are executing the training then sharing the models on centralized platforms such as HuggingFace and torch.hub. The goal of this work is to identify several key adversarial vulnerabilities of these models in an effort to make future designs more robust. Intuitively, our attacks manipulate deep feature representations to fool an out-of-distribution (OOD) detector which will be required when using these open-world-aware models to solve closed-set downstream tasks. Our methods reliably make in-distribution (ID) images (w.r.t. a downstream task) be predicted as OOD and vice versa while existing in extremely low-knowledge-assumption threat models. We show our attacks to be potent in whitebox and blackbox settings, as well as when transferred across foundational model types (e.g., attack DINOv2 with CLIP)! This work is only just the beginning of a long journey towards adversarially robust foundational vision models.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models
Vision-language models (VLMs) have achieved significant strides in recent times specially in multimodal tasks, yet they remain susceptible to adversarial attacks on their vision components. To address this, we propose Si…
SpecificityPA-Attack: Guiding Gray-Box Attacks on LVLM Vision Encoders with Prototypes and Attention
Large Vision-Language Models (LVLMs) are foundational to modern multimodal applications, yet their susceptibility to adversarial attacks remains a critical concern. Prior white-box attacks rarely generalize across tasks,…
Foundational Models Defining a New Era in Vision: A Survey and Outlook
Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world. The complex relations between objects and their locations, ambiguities, and variations in the r…
BenchmarkingIn and Out-of-Domain Text Adversarial Robustness via Label Smoothing
Recently it has been shown that state-of-the-art NLP models are vulnerable to adversarial attacks, where the predictions of a model can be drastically altered by slight modifications to the input (such as synonym substit…
Adversarial RobustnessHolistic Adversarial Robustness of Deep Learning Models
Adversarial robustness studies the worst-case performance of a machine learning model to ensure safety and reliability. With the proliferation of deep-learning-based technology, the potential risks associated with model …
Adversarial RobustnessDeep Learning