On Adversarial Robustness of Language Models in Transfer Learning
원문 초록
We investigate the adversarial robustness of LLMs in transfer learning scenarios. Through comprehensive experiments on multiple datasets (MBIB Hate Speech, MBIB Political Bias, MBIB Gender Bias) and various model architectures (BERT, RoBERTa, GPT-2, Gemma, Phi), we reveal that transfer learning, while improving standard performance metrics, often leads to increased vulnerability to adversarial attacks. Our findings demonstrate that larger models exhibit greater resilience to this phenomenon, suggesting a complex interplay between model size, architecture, and adaptation methods. Our work highlights the crucial need for considering adversarial robustness in transfer learning scenarios and provides insights into maintaining model security without compromising performance. These findings have significant implications for the development and deployment of LLMs in real-world applications where both performance and robustness are paramount.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors
RaMen: Multi-Strategy Multi-Modal Learning for Bundle Construction
Best Practices for Large-Scale, Pixel-Wise Crop Mapping and Transfer Learning Workflows
Robust-Multi-Task Gradient Boosting
Bridging Robustness and Generalization Against Word Substitution Attacks in NLP via the Growth Bound Matrix Approach
PSAT: Pediatric Segmentation Approaches via Adult Augmentations and Transfer Learning
토론
이 논문과 연결된 포럼 글이 아직 없습니다.