paper-with-me

Papers

AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning

2024-07-30 · Maisha Binte Rashid, Pablo Rivas

Multimodal machine learning models that combine visual and textual data are increasingly being deployed in critical applications, raising significant safety and security concerns due to their vulnerability to adversarial attacks. This paper presents an effective strategy to enhance the robustness of multimodal image captioning models against such attacks. By leveraging the Fast Gradient Sign Method (FGSM) to generate adversarial examples and incorporating adversarial training techniques, we demonstrate improved model robustness on two benchmark datasets: Flickr8k and COCO. Our findings indicate that selectively training only the text decoder of the multimodal architecture shows performance comparable to full adversarial training while offering increased computational efficiency. This targeted approach suggests a balance between robustness and training costs, facilitating the ethical deployment of multimodal AI systems across various domains.

📄 PDF Abstract BibTeX arXiv:2407.21174

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial RobustnessComputational EfficiencyDecoderImage Captioning

Similar Papers 제목 키워드 기반

Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trends

2025-04-21 · Mohammad Abu Tami, Mohammed Elhenawy, Huthaifa I. Ashqar

Traffic safety remains a critical global challenge, with traditional Advanced Driver-Assistance Systems (ADAS) often struggling in dynamic real-world scenarios due to fragmented sensor processing and susceptibility to ad…

Adversarial RobustnessDecision MakingScene Understanding

MMT-ARD: Multimodal Multi-Teacher Adversarial Distillation for Robust Vision-Language Models

2025-11-21 · Yuqi Li, Junhao Dong, Chuanguang Yang, Shiping Wen 외 arxiv

Vision-Language Models (VLMs) are increasingly deployed in safety-critical applications, making their adversarial robustness a crucial concern. While adversarial knowledge distillation has shown promise in transferring r…

Adversarial RobustnessKnowledge Distillation

Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety

2026-06-23 · Shikai Qiu, Xiaowen Xu, Benlei Cui, Ting Ma 외 arxiv

General-purpose models often struggle to reliably identify and understand real-world multimodal risks, largely due to the inherent multimodal adversarial nature of content and AI safety. We present Yuvion VL, a family of…

Adversarial Robustness

Calibrated Adversarial Sampling: Multi-Armed Bandit-Guided Generalization Against Unforeseen Attacks

2025-11-15 · Rui Wang, Zeming Wei, Xiyue Zhang, Meng Sun arxiv

Deep Neural Networks (DNNs) are known to be vulnerable to various adversarial perturbations. To address the safety concerns arising from these vulnerabilities, adversarial training (AT) has emerged as one of the most eff…

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