paper-with-me

홈 › Papers

Vision-LLMs Can Fool Themselves with Self-Generated Typographic Attacks

2024-02-01 · Maan Qraitem, Nazia Tasnim, Piotr Teterwak, Kate Saenko, Bryan A. Plummer

Typographic attacks, adding misleading text to images, can deceive vision-language models (LVLMs). The susceptibility of recent large LVLMs like GPT4-V to such attacks is understudied, raising concerns about amplified misinformation in personal assistant applications. Previous attacks use simple strategies, such as random misleading words, which don't fully exploit LVLMs' language reasoning abilities. We introduce an experimental setup for testing typographic attacks on LVLMs and propose two novel self-generated attacks: (1) Class-based attacks, where the model identifies a similar class to deceive itself, and (2) Reasoned attacks, where an advanced LVLM suggests an attack combining a deceiving class and description. Our experiments show these attacks significantly reduce classification performance by up to 60\% and are effective across different models, including InstructBLIP and MiniGPT4. Code: https://github.com/mqraitem/Self-Gen-Typo-Attack

📄 PDF Abstract BibTeX arXiv:2402.00626

Code (1)

mqraitem/self-gen-typo-attack 공식 구현 pytorch

Tasks

DescriptiveMisinformation

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
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

Guiding LLM to Fool Itself: Automatically Manipulating Machine Reading Comprehension Shortcut Triggers

2023-10-24 · Mosh Levy, Shauli Ravfogel, Yoav Goldberg

Recent applications of LLMs in Machine Reading Comprehension (MRC) systems have shown impressive results, but the use of shortcuts, mechanisms triggered by features spuriously correlated to the true label, has emerged as…

Machine Reading ComprehensionReading Comprehension

Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients

2017-11-26 · Andrew Slavin Ross, Finale Doshi-Velez

Deep neural networks have proven remarkably effective at solving many classification problems, but have been criticized recently for two major weaknesses: the reasons behind their predictions are uninterpretable, and the…

Adversarial Robustness

Internalized Self-Correction for Large Language Models

2024-12-21 · Nishanth Upadhyaya, Raghavendra Sridharamurthy

In this article, we introduce 'Internalized Self-Correction' (InSeC) for large language models (LLMs). While many approaches exist for self-reflection at inference time, we propose a novel method that combines ideas from…

Instruction Following

Not the Example, but the Process: How Self-Generated Examples Enhance LLM Reasoning

2026-01-26 · Daehoon Gwak, Minseo Jung, Junwoo Park, Minho Park 외 arxiv

Recent studies have shown that Large Language Models (LLMs) can improve their reasoning performance through self-generated few-shot examples, achieving results comparable to manually curated in-context examples. However,…

A Wolf in Sheep's Clothing: Generalized Nested Jailbreak Prompts can Fool Large Language Models Easily

2023-11-14 · Peng Ding, Jun Kuang, Dan Ma, Xuezhi Cao 외

Large Language Models (LLMs), such as ChatGPT and GPT-4, are designed to provide useful and safe responses. However, adversarial prompts known as 'jailbreaks' can circumvent safeguards, leading LLMs to generate potential…