13 citations · 31 across the 10 of their papers we have counts for
6 papers · 1 filter
UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Data
Justin Li, Efe Sencan, Jasper Zheng Duan +3
Machine learning models, particularly deep neural networks, have demonstrated strong performance in classifying complex time series data. However, their black-box nature limits tru…
Rethinking Individual Fairness in Deepfake Detection
Aryana Hou, Li Lin, Justin Li +1
Generative AI models have substantially improved the realism of synthetic media, yet their misuse through sophisticated DeepFakes poses significant risks. Despite recent advances i…
The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
Nathaniel Li, Alexander Pan, Anjali Gopal +54
The White House Executive Order on Artificial Intelligence highlights the risks of large language models (LLMs) empowering malicious actors in developing biological, cyber, and che…
On Achieving Optimal Adversarial Test Error
Justin D. Li, Matus Telgarsky
We first elucidate various fundamental properties of optimal adversarial predictors: the structure of optimal adversarial convex predictors in terms of optimal adversarial zero-one…
Predicting the Stereoselectivity of Chemical Transformations by Machine Learning
Justin Li, Dakang Zhang, Yifei Wang +3
Stereoselective reactions (both chemical and enzymatic reactions) have been essential for origin of life, evolution, human biology and medicine. Since late 1960s, there have been n…
Early-stopped neural networks are consistent
Ziwei Ji, Justin D. Li, Matus Telgarsky
This work studies the behavior of shallow ReLU networks trained with the logistic loss via gradient descent on binary classification data where the underlying data distribution is…