Search Results for author:
Found 6 papers, 2 papers with code
Evaluating and Mitigating Linguistic Discrimination in Large Language Models
The results show that LLMs exhibit stronger human alignment capabilities with queries in English, French, Russian, and Spanish (only 1. 04\% of harmful queries successfully jailbreak on average) compared to queries in Bengali, Georgian, Nepali and Maithili (27. 7\% of harmful queries jailbreak successfully on average).
Repairing Adversarial Texts through Perturbation
Furthermore, such attacks are impossible to eliminate, i. e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training.
Automatic Fairness Testing of Neural Classifiers through Adversarial Sampling
In this work, we bridge the gap by proposing a scalable and effective approach for systematically searching for discriminatory samples while extending existing fairness testing approaches to address a more challenging domain, i. e., text classification.
Towards Repairing Neural Networks Correctly
Neural networks are increasingly applied to support decision making in safety-critical applications (like autonomous cars, unmanned aerial vehicles and face recognition based authentication).
Towards Interpreting Recurrent Neural Networks through Probabilistic Abstraction
In this work, we propose an approach to extract probabilistic automata for interpreting an important class of neural networks, i. e., recurrent neural networks.
Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing
We thus first propose a measure of `sensitivity' and show empirically that normal samples and adversarial samples have distinguishable sensitivity.
