paper-with-me

Papers

Reading Isn't Believing: Adversarial Attacks On Multi-Modal Neurons

2021-03-18 · David A. Noever, Samantha E. Miller Noever

With Open AI's publishing of their CLIP model (Contrastive Language-Image Pre-training), multi-modal neural networks now provide accessible models that combine reading with visual recognition. Their network offers novel ways to probe its dual abilities to read text while classifying visual objects. This paper demonstrates several new categories of adversarial attacks, spanning basic typographical, conceptual, and iconographic inputs generated to fool the model into making false or absurd classifications. We demonstrate that contradictory text and image signals can confuse the model into choosing false (visual) options. Like previous authors, we show by example that the CLIP model tends to read first, look later, a phenomenon we describe as reading isn't believing.

📄 PDF Abstract BibTeX arXiv:2103.10480

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

Seeing Isn't Believing: Context-Aware Adversarial Patch Synthesis via Conditional GAN

2025-09-26 · Roie Kazoom, Alon Goldberg, Hodaya Cohen, Ofer Hadar arxiv

Adversarial patch attacks pose a severe threat to deep neural networks, yet most existing approaches rely on unrealistic white-box assumptions, untargeted objectives, or produce visually conspicuous patches that limit re…

Adversarial Robustness

Seeing is Believing? Evaluating Vision-Language Model Susceptibility in Agent-to-Agent Multimodal Persuasion

2025-10-26 · Haoyi Qiu, Yilun Zhou, Pranav Narayanan Venkit, Kung-Hsiang Huang 외 arxiv

As autonomous agents increasingly interact, they inevitably attempt to influence one another. While prior work in text-only settings has explored the dynamics of Agent-to-Agent (A2A) persuasion, the rise of Vision-Langua…

Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective

2024-04-30 · Wanqi Zhou, Shuanghao Bai, Danilo P. Mandic, Qibin Zhao 외

Pretrained vision-language models (VLMs) like CLIP exhibit exceptional generalization across diverse downstream tasks. While recent studies reveal their vulnerability to adversarial attacks, research to date has primaril…

Adversarial DefenseAdversarial RobustnessAdversarial Text

One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image

2025-04-02 · Ezzeldin Shereen, Dan Ristea, Shae McFadden, Burak Hasircioglu 외

Multi-modal retrieval augmented generation (M-RAG) is instrumental for inhibiting hallucinations in large multi-modal models (LMMs) through the use of a factual knowledge base (KB). However, M-RAG introduces new attack v…

AllMisinformationRAGRetrieval+1

Benchmarking Robustness of Machine Reading Comprehension Models

2020-04-29 · Findings (ACL) 2021 8 · Chenglei Si, Ziqing Yang, Yiming Cui, Wentao Ma 외

Machine Reading Comprehension (MRC) is an important testbed for evaluating models' natural language understanding (NLU) ability. There has been rapid progress in this area, with new models achieving impressive performanc…

BenchmarkingMachine Reading ComprehensionNatural Language UnderstandingReading Comprehension