paper-with-me

Papers

Adversarially Pretrained Transformers may be Universally Robust In-Context Learners

2025-05-20 · Soichiro Kumano, Hiroshi Kera, Toshihiko Yamasaki

Adversarial training is one of the most effective adversarial defenses, but it incurs a high computational cost. In this study, we show that transformers adversarially pretrained on diverse tasks can serve as robust foundation models and eliminate the need for adversarial training in downstream tasks. Specifically, we theoretically demonstrate that through in-context learning, a single adversarially pretrained transformer can robustly generalize to multiple unseen tasks without any additional training, i.e., without any parameter updates. This robustness stems from the model's focus on robust features and its resistance to attacks that exploit non-predictive features. Besides these positive findings, we also identify several limitations. Under certain conditions (though unrealistic), no universally robust single-layer transformers exist. Moreover, robust transformers exhibit an accuracy--robustness trade-off and require a large number of in-context demonstrations. The code is available at https://github.com/s-kumano/universally-robust-in-context-learner.

📄 PDF Abstract BibTeX arXiv:2505.14042

Code (1)

s-kumano/universally-robust-in-context-learner 공식 구현 pytorch

Tasks

In-Context Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Transformers are Minimax Optimal Nonparametric In-Context Learners

2024-08-22 · Juno Kim, Tai Nakamaki, Taiji Suzuki

In-context learning (ICL) of large language models has proven to be a surprisingly effective method of learning a new task from only a few demonstrative examples. In this paper, we study the efficacy of ICL from the view…

DiversityIn-Context LearningLearning TheoryRepresentation Learning

Can Graphs Improve Tabular Foundation Models?

2025-12-13 · Franck Le, Keith Grueneberg, Erich Nahum, Vadim Sheinin arxiv

Tabular data are central to many real-world systems. While recent tabular transformers and in-context learners such as SAINT, TP-BERTa, TabPFN, TabICL, and MITRA incorporate limited inter-row reasoning, most approaches s…

Revisiting Pretraining for Semi-Supervised Learning in the Low-Label Regime

2022-05-06 · Xun Xu, Jingyi Liao, Lile Cai, Manh Cuong Nguyen 외

Semi-supervised learning (SSL) addresses the lack of labeled data by exploiting large unlabeled data through pseudolabeling. However, in the extremely low-label regime, pseudo labels could be incorrect, a.k.a. the confir…

What learning algorithm is in-context learning? Investigations with linear models

2022-11-28 · Ekin Akyürek, Dale Schuurmans, Jacob Andreas, Tengyu Ma 외

Neural sequence models, especially transformers, exhibit a remarkable capacity for in-context learning. They can construct new predictors from sequences of labeled examples $(x, f(x))$ presented in the input without furt…

In-Context Learningregression

Compositional generalization in semantic parsing with pretrained transformers

2021-09-30 · A. Emin Orhan

Large-scale pretraining instills large amounts of knowledge in deep neural networks. This, in turn, improves the generalization behavior of these models in downstream tasks. What exactly are the limits to the generalizat…

Out-of-Distribution GeneralizationSemantic Parsing