paper-with-me

Papers

AnyAttack: Towards Large-scale Self-supervised Adversarial Attacks on Vision-language Models

2024-10-07 · CVPR 2025 1 · Jiaming Zhang, Junhong Ye, Xingjun Ma, Yige Li, Yunfan Yang, Yunhao Chen, Jitao Sang, Dit-yan Yeung

Due to their multimodal capabilities, Vision-Language Models (VLMs) have found numerous impactful applications in real-world scenarios. However, recent studies have revealed that VLMs are vulnerable to image-based adversarial attacks. Traditional targeted adversarial attacks require specific targets and labels, limiting their real-world impact.We present AnyAttack, a self-supervised framework that transcends the limitations of conventional attacks through a novel foundation model approach. By pre-training on the massive LAION-400M dataset without label supervision, AnyAttack achieves unprecedented flexibility - enabling any image to be transformed into an attack vector targeting any desired output across different VLMs.This approach fundamentally changes the threat landscape, making adversarial capabilities accessible at an unprecedented scale. Our extensive validation across five open-source VLMs (CLIP, BLIP, BLIP2, InstructBLIP, and MiniGPT-4) demonstrates AnyAttack's effectiveness across diverse multimodal tasks. Most concerning, AnyAttack seamlessly transfers to commercial systems including Google Gemini, Claude Sonnet, Microsoft Copilot and OpenAI GPT, revealing a systemic vulnerability requiring immediate attention.

📄 PDF Abstract BibTeX arXiv:2410.05346

Code (0)

등록된 구현이 없습니다.

Tasks

Image CaptioningImage-text RetrievalText Retrieval

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Attention 설명 없음
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Residual Connection 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Weight Decay 설명 없음

Similar Papers 제목 키워드 기반

SSAH: Semi-supervised Adversarial Deep Hashing with Self-paced Hard Sample Generation

2019-11-20 · Sheng Jin, Shangchen Zhou, Yao Liu, Chao Chen 외

Deep hashing methods have been proved to be effective and efficient for large-scale Web media search. The success of these data-driven methods largely depends on collecting sufficient labeled data, which is usually a cru…

Deep HashingGenerative Adversarial Network

Domain Confusion with Self Ensembling for Unsupervised Adaptation

2018-10-10 · Jiawei Wang, Zhaoshui He, Chengjian Feng, Zhouping Zhu 외

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There …

Domain AdaptationUnsupervised Domain Adaptation

VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models

2026-05-02 · Pang Liu, Yingjie Lao arxiv

Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is highly vulnerable to imperceptible pert…

Adversarial Attack

Adversarial Self-Supervised Data-Free Distillation for Text Classification

2020-10-10 · EMNLP 2020 11 · Xinyin Ma, Yongliang Shen, Gongfan Fang, Chen Chen 외

Large pre-trained transformer-based language models have achieved impressive results on a wide range of NLP tasks. In the past few years, Knowledge Distillation(KD) has become a popular paradigm to compress a computation…

ClassificationGeneral ClassificationKnowledge Distillationtext-classification+2

The Impact of Scaling Training Data on Adversarial Robustness

2025-09-30 · Marco Zimmerli, Andreas Plesner, Till Aczel, Roger Wattenhofer arxiv

Deep neural networks remain vulnerable to adversarial examples despite advances in architectures and training paradigms. We investigate how training data characteristics affect adversarial robustness across 36 state-of-t…

Adversarial RobustnessContrastive Learning