4 citations · 4 across the 6 of their papers we have counts for
6 papers
Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models
Yuda Song, Hanlin Zhang, Carson Eisenach +3
Self-improvement is a mechanism in Large Language Model (LLM) pre-training, post-training and test-time inference. We explore a framework where the model verifies its own outputs,…
Fuzziness-tuned: Improving the Transferability of Adversarial Examples
Xiangyuan Yang, Jie Lin, Hanlin Zhang +2
With the development of adversarial attacks, adversairal examples have been widely used to enhance the robustness of the training models on deep neural networks. Although considera…
Improving the Transferability of Adversarial Examples via Direction Tuning
Xiangyuan Yang, Jie Lin, Hanlin Zhang +2
In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although conside…
Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction
Xiangyuan Yang, Jie Lin, Hanlin Zhang +2
Deep neural networks are easily attacked by imperceptible perturbation. Presently, adversarial training (AT) is the most effective method to enhance the robustness of the model aga…
FACM: Intermediate Layer Still Retain Effective Features against Adversarial Examples
Xiangyuan Yang, Jie Lin, Hanlin Zhang +2
In strong adversarial attacks against deep neural networks (DNN), the generated adversarial example will mislead the DNN-implemented classifier by destroying the output features of…
Gradient Aligned Attacks via a Few Queries
Xiangyuan Yang, Jie Lin, Hanlin Zhang +2
Black-box query attacks, which rely only on the output of the victim model, have proven to be effective in attacking deep learning models. However, existing black-box query attacks…