AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909274885586944 |
|---|---|
| author | Rashid, Maisha Binte Rivas, Pablo |
| author_facet | Rashid, Maisha Binte Rivas, Pablo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_21174 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning Rashid, Maisha Binte Rivas, Pablo Computer Vision and Pattern Recognition Artificial Intelligence Audio and Speech Processing I.2.7 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. |
| title | AI Safety in Practice: Enhancing Adversarial Robustness in Multimodal Image Captioning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Audio and Speech Processing I.2.7 |
| url | https://arxiv.org/abs/2407.21174 |