paper-with-me

홈 › Papers

Playing Devil's Advocate: Unmasking Toxicity and Vulnerabilities in Large Vision-Language Models

2025-01-14 · Abdulkadir Erol, Trilok Padhi, Agnik Saha, Ugur Kursuncu, Mehmet Emin Aktas

The rapid advancement of Large Vision-Language Models (LVLMs) has enhanced capabilities offering potential applications from content creation to productivity enhancement. Despite their innovative potential, LVLMs exhibit vulnerabilities, especially in generating potentially toxic or unsafe responses. Malicious actors can exploit these vulnerabilities to propagate toxic content in an automated (or semi-) manner, leveraging the susceptibility of LVLMs to deception via strategically crafted prompts without fine-tuning or compute-intensive procedures. Despite the red-teaming efforts and inherent potential risks associated with the LVLMs, exploring vulnerabilities of LVLMs remains nascent and yet to be fully addressed in a systematic manner. This study systematically examines the vulnerabilities of open-source LVLMs, including LLaVA, InstructBLIP, Fuyu, and Qwen, using adversarial prompt strategies that simulate real-world social manipulation tactics informed by social theories. Our findings show that (i) toxicity and insulting are the most prevalent behaviors, with the mean rates of 16.13% and 9.75%, respectively; (ii) Qwen-VL-Chat, LLaVA-v1.6-Vicuna-7b, and InstructBLIP-Vicuna-7b are the most vulnerable models, exhibiting toxic response rates of 21.50%, 18.30% and 17.90%, and insulting responses of 13.40%, 11.70% and 10.10%, respectively; (iii) prompting strategies incorporating dark humor and multimodal toxic prompt completion significantly elevated these vulnerabilities. Despite being fine-tuned for safety, these models still generate content with varying degrees of toxicity when prompted with adversarial inputs, highlighting the urgent need for enhanced safety mechanisms and robust guardrails in LVLM development.

📄 PDF Abstract BibTeX arXiv:2501.09039

Code (0)

등록된 구현이 없습니다.

Tasks

Red Teaming

Similar Papers 제목 키워드 기반

Playing Devil's Advocate: Off-the-Shelf Persona Vectors Rival Targeted Steering for Sycophancy

2026-05-20 · Ishaan Kelkar, Nebras Alam, Vikram Kakaria, Madhur Panwar 외 arxiv

We study the effect of different persona on \textbf{sycophancy}: model's agreement with users even when the user is incorrect. The standard mitigation, Contrastive Activation Addition (CAA), derives a steering direction …

Devil’s Advocate: Novel Boosting Ensemble Method from Psychological Findings for Text Classification

2021-11-01 · Findings (EMNLP) 2021 11 · Hwiyeol Jo, Jaeseo Lim, Byoung-Tak Zhang

We present a new form of ensemble method–Devil’s Advocate, which uses a deliberately dissenting model to force other submodels within the ensemble to better collaborate. Our method consists of two different training sett…

text-classificationText Classification

DEBATE: Devil's Advocate-Based Assessment and Text Evaluation

2024-05-16 · Alex Kim, Keonwoo Kim, Sangwon Yoon

As natural language generation (NLG) models have become prevalent, systematically assessing the quality of machine-generated texts has become increasingly important. Recent studies introduce LLM-based evaluators that ope…

nlg evaluationText Generation

Don't Just Translate, Agitate: Using Large Language Models as Devil's Advocates for AI Explanations

2025-04-16 · Ashley Suh, Kenneth Alperin, Harry Li, Steven R Gomez

This position paper highlights a growing trend in Explainable AI (XAI) research where Large Language Models (LLMs) are used to translate outputs from explainability techniques, like feature-attribution weights, into a na…

Goodtriever: Adaptive Toxicity Mitigation with Retrieval-augmented Models

2023-10-11 · Luiza Pozzobon, Beyza Ermis, Patrick Lewis, Sara Hooker

Considerable effort has been dedicated to mitigating toxicity, but existing methods often require drastic modifications to model parameters or the use of computationally intensive auxiliary models. Furthermore, previous …

RetrievalText Generation