Zobrazeno 1 - 10
of 16
pro vyhledávání: '"Xu, Xilie"'
This technical report introduces our top-ranked solution that employs two approaches, \ie suffix injection and projected gradient descent (PGD) , to address the TiFA workshop MLLM attack challenge. Specifically, we first append the text from an incor
Externí odkaz:
http://arxiv.org/abs/2412.15614
Low-rank adaptation (LoRA) is an efficient strategy for adapting latent diffusion models (LDMs) on a private dataset to generate specific images by minimizing the adaptation loss. However, the LoRA-adapted LDMs are vulnerable to membership inference
Externí odkaz:
http://arxiv.org/abs/2402.11989
The wide-ranging applications of large language models (LLMs), especially in safety-critical domains, necessitate the proper evaluation of the LLM's adversarial robustness. This paper proposes an efficient tool to audit the LLM's adversarial robustne
Externí odkaz:
http://arxiv.org/abs/2310.13345
Robust Fine-Tuning (RFT) is a low-cost strategy to obtain adversarial robustness in downstream applications, without requiring a lot of computational resources and collecting significant amounts of data. This paper uncovers an issue with the existing
Externí odkaz:
http://arxiv.org/abs/2310.01818
Adversarial contrastive learning (ACL) is a technique that enhances standard contrastive learning (SCL) by incorporating adversarial data to learn a robust representation that can withstand adversarial attacks and common corruptions without requiring
Externí odkaz:
http://arxiv.org/abs/2305.00374
Adversarial contrastive learning (ACL) does not require expensive data annotations but outputs a robust representation that withstands adversarial attacks and also generalizes to a wide range of downstream tasks. However, ACL needs tremendous running
Externí odkaz:
http://arxiv.org/abs/2302.03857
Non-parametric two-sample tests (TSTs) that judge whether two sets of samples are drawn from the same distribution, have been widely used in the analysis of critical data. People tend to employ TSTs as trusted basic tools and rarely have any doubt ab
Externí odkaz:
http://arxiv.org/abs/2202.03077
Autor:
Zhang, Jingfeng, Xu, Xilie, Han, Bo, Liu, Tongliang, Niu, Gang, Cui, Lizhen, Sugiyama, Masashi
Publikováno v:
Transactions on Machine Learning Research, 2022
Adversarial training (AT) formulated as the minimax optimization problem can effectively enhance the model's robustness against adversarial attacks. The existing AT methods mainly focused on manipulating the inner maximization for generating quality
Externí odkaz:
http://arxiv.org/abs/2105.14676
Autor:
Chen, Chen, Zhang, Jingfeng, Xu, Xilie, Hu, Tianlei, Niu, Gang, Chen, Gang, Sugiyama, Masashi
To enhance adversarial robustness, adversarial training learns deep neural networks on the adversarial variants generated by their natural data. However, as the training progresses, the training data becomes less and less attackable, undermining the
Externí odkaz:
http://arxiv.org/abs/2102.07327
Autor:
Zhang, Jingfeng, Xu, Xilie, Han, Bo, Niu, Gang, Cui, Lizhen, Sugiyama, Masashi, Kankanhalli, Mohan
Adversarial training based on the minimax formulation is necessary for obtaining adversarial robustness of trained models. However, it is conservative or even pessimistic so that it sometimes hurts the natural generalization. In this paper, we raise
Externí odkaz:
http://arxiv.org/abs/2002.11242