AutoRedTrader generates synthetic financial misinformation via behavioral bias manipulation and agent feedback to red-team LLM trading agents, reaching 69% exposure and 26.67% attack success on Bitcoin data simulations.
MIT Press, 2016
5 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
SKOP uses key-orthogonal projections to steer LLM activations while preserving attention patterns on focus tokens, cutting utility degradation by 5-7x and retaining over 95% of standard steering efficacy.
A rank reduction autoencoder combined with classification predicts numerical dispersion in automotive crash simulations more effectively than random forests when using wavelet or slope signal inputs.
Hybrid PCA-neural network classifiers trained on full CMB maps, interpreted via SHAP to identify spatial signatures distinguishing LambdaCDM from primordial feature models.
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.
citing papers explorer
-
AutoRedTrader: Autonomous Red Teaming of Trading Agents through Synthetic Misinformation Injection
AutoRedTrader generates synthetic financial misinformation via behavioral bias manipulation and agent feedback to red-team LLM trading agents, reaching 69% exposure and 26.67% attack success on Bitcoin data simulations.
-
Don't Lose Focus: Activation Steering via Key-Orthogonal Projections
SKOP uses key-orthogonal projections to steer LLM activations while preserving attention patterns on focus tokens, cutting utility degradation by 5-7x and retaining over 95% of standard steering efficacy.
-
CRADIPOR: Crash Dispersion Predictor
A rank reduction autoencoder combined with classification predicts numerical dispersion in automotive crash simulations more effectively than random forests when using wavelet or slope signal inputs.
-
Explaining Neural Networks on the Sky: Machine Learning Interpretability for Cosmic Microwave Background Maps
Hybrid PCA-neural network classifiers trained on full CMB maps, interpreted via SHAP to identify spatial signatures distinguishing LambdaCDM from primordial feature models.
-
Sharpness-Aware Minimization with Z-Score Gradient Filtering
Z-Score Filtered SAM retains only high absolute Z-score gradient components per layer during the ascent step and reports higher test accuracy than standard SAM on CIFAR and Tiny-ImageNet benchmarks.