1 code implementation • 6 Feb 2024 • Mantas Mazeika, Long Phan, Xuwang Yin, Andy Zou, Zifan Wang, Norman Mu, Elham Sakhaee, Nathaniel Li, Steven Basart, Bo Li, David Forsyth, Dan Hendrycks
Automated red teaming holds substantial promise for uncovering and mitigating the risks associated with the malicious use of large language models (LLMs), yet the field lacks a standardized evaluation framework to rigorously assess new methods.
no code implementations • 12 Nov 2023 • Xuwang Yin
Key contributions include: (1) an adversarial attack strategy tailored to text to generate negative samples, circumventing MCMC limitations; (2) an adversarial training algorithm for EBMs leveraging these attacks; (3) empirical validation of performance improvements on a sequence generation task.
1 code implementation • 2 Oct 2023 • Andy Zou, Long Phan, Sarah Chen, James Campbell, Phillip Guo, Richard Ren, Alexander Pan, Xuwang Yin, Mantas Mazeika, Ann-Kathrin Dombrowski, Shashwat Goel, Nathaniel Li, Michael J. Byun, Zifan Wang, Alex Mallen, Steven Basart, Sanmi Koyejo, Dawn Song, Matt Fredrikson, J. Zico Kolter, Dan Hendrycks
In this paper, we identify and characterize the emerging area of representation engineering (RepE), an approach to enhancing the transparency of AI systems that draws on insights from cognitive neuroscience.
Ranked #3 on Question Answering on TruthfulQA
no code implementations • 14 Dec 2022 • Xuwang Yin
Training adversarially robust discriminative (i. e., softmax) classifier has been the dominant approach to robust classification.
1 code implementation • 30 Apr 2022 • Abu Hasnat Mohammad Rubaiyat, Shiying Li, Xuwang Yin, Mohammad Shifat E Rabbi, Yan Zhuang, Gustavo K. Rohde
This paper presents a new end-to-end signal classification method using the signed cumulative distribution transform (SCDT).
1 code implementation • 22 Feb 2022 • Yan Zhuang, Shiying Li, Mohammad Shifat-E-Rabbi, Xuwang Yin, Abu Hasnat Mohammad Rubaiyat, Gustavo K. Rohde
Face recognition is then performed using a nearest subspace in R-CDT domain of local gradient distributions.
2 code implementations • 9 Jan 2022 • Mohammad Shifat E Rabbi, Yan Zhuang, Shiying Li, Abu Hasnat Mohammad Rubaiyat, Xuwang Yin, Gustavo K. Rohde
However, they are known to underperform when training data are limited and thus require data augmentation strategies that render the method computationally expensive and not always effective.
1 code implementation • 11 Dec 2020 • Xuwang Yin, Shiying Li, Gustavo K. Rohde
We study a new approach to learning energy-based models (EBMs) based on adversarial training (AT).
no code implementations • ICLR 2020 • Xuwang Yin, Soheil Kolouri, Gustavo K. Rohde
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
3 code implementations • 7 Apr 2020 • Mohammad Shifat-E-Rabbi, Xuwang Yin, Abu Hasnat Mohammad Rubaiyat, Shiying Li, Soheil Kolouri, Akram Aldroubi, Jonathan M. Nichols, Gustavo K. Rohde
We present a new supervised image classification method applicable to a broad class of image deformation models.
3 code implementations • 21 Aug 2019 • Max Kaufmann, Daniel Kang, Yi Sun, Steven Basart, Xuwang Yin, Mantas Mazeika, Akul Arora, Adam Dziedzic, Franziska Boenisch, Tom Brown, Jacob Steinhardt, Dan Hendrycks
To narrow in on this discrepancy between research and reality we introduce ImageNet-UA, a framework for evaluating model robustness against a range of unforeseen adversaries, including eighteen new non-L_p attacks.
1 code implementation • 4 Jul 2019 • Soheil Kolouri, Xuwang Yin, Gustavo K. Rohde
Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks.
1 code implementation • 7 Jun 2019 • Mohammad Shifat-E-Rabbi, Xuwang Yin, Cailey Elizabeth Fitzgerald, Gustavo K. Rohde
Cell image classification methods are currently being used in numerous applications in cell biology and medicine.
1 code implementation • 27 May 2019 • Xuwang Yin, Soheil Kolouri, Gustavo K. Rohde
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
no code implementations • NAACL 2019 • Paola Cascante-Bonilla, Xuwang Yin, Vicente Ordonez, Song Feng
In this paper we introduce Chat-crowd, an interactive environment for visual layout composition via conversational interactions.
no code implementations • 7 Dec 2018 • Jianfeng Chi, Emmanuel Owusu, Xuwang Yin, Tong Yu, William Chan, Patrick Tague, Yuan Tian
We present a practical method for protecting data during the inference phase of deep learning based on bipartite topology threat modeling and an interactive adversarial deep network construction.
no code implementations • EMNLP 2017 • Xuwang Yin, Vicente Ordonez
Generating captions for images is a task that has recently received considerable attention.
no code implementations • 11 Jan 2013 • Xu-Cheng Yin, Xuwang Yin, Kai-Zhu Huang, Hong-Wei Hao
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks.