Search Results for author:
Found 3 papers, 1 papers with code
Adversarial Feature Alignment: Balancing Robustness and Accuracy in Deep Learning via Adversarial Training
Deep learning models continue to advance in accuracy, yet they remain vulnerable to adversarial attacks, which often lead to the misclassification of adversarial examples.
CovRL: Fuzzing JavaScript Engines with Coverage-Guided Reinforcement Learning for LLM-based Mutation
This map is key in calculating the fuzzing reward, which is then applied to the LLM-based mutator through reinforcement learning.
Amplifying Training Data Exposure through Fine-Tuning with Pseudo-Labeled Memberships
To address this, we propose the use of pseudo-labels for these generated texts, leveraging membership approximations indicated by machine-generated probabilities from the target LM.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
