Search Results for author:
Found 18 papers, 11 papers with code
HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
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.
Learning Globally Optimized Language Structure via Adversarial Training
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.
Representation Engineering: A Top-Down Approach to AI Transparency
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
Generative Robust Classification
Training adversarially robust discriminative (i. e., softmax) classifier has been the dominant approach to robust classification.
End-to-End Signal Classification in Signed Cumulative Distribution Transform Space
This paper presents a new end-to-end signal classification method using the signed cumulative distribution transform (SCDT).
Local Sliced-Wasserstein Feature Sets for Illumination-invariant Face Recognition
Face recognition is then performed using a nearest subspace in R-CDT domain of local gradient distributions.
Invariance encoding in sliced-Wasserstein space for image classification with limited training data
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.
Learning Energy-Based Models With Adversarial Training
We study a new approach to learning energy-based models (EBMs) based on adversarial training (AT).
GAT: Generative Adversarial Training for Adversarial Example Detection and Classification
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
Radon cumulative distribution transform subspace modeling for image classification
We present a new supervised image classification method applicable to a broad class of image deformation models.
Testing Robustness Against Unforeseen Adversaries
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.
Neural Networks, Hypersurfaces, and Radon Transforms
Connections between integration along hypersufaces, Radon transforms, and neural networks are exploited to highlight an integral geometric mathematical interpretation of neural networks.
Cell image classification: a comparative overview
Cell image classification methods are currently being used in numerous applications in cell biology and medicine.
GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification
The vulnerabilities of deep neural networks against adversarial examples have become a significant concern for deploying these models in sensitive domains.
Chat-crowd: A Dialog-based Platform for Visual Layout Composition
In this paper we introduce Chat-crowd, an interactive environment for visual layout composition via conversational interactions.
Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase
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.
OBJ2TEXT: Generating Visually Descriptive Language from Object Layouts
Generating captions for images is a task that has recently received considerable attention.
Robust Text Detection in Natural Scene Images
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks.
