Search Results for author:
Found 9 papers, 2 papers with code
CLIBE: Detecting Dynamic Backdoors in Transformer-based NLP Models
CLIBE injects a "few-shot perturbation" into the suspect Transformer model by crafting optimized weight perturbation in the attention layers to make the perturbed model classify a limited number of reference samples as a target label.
SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems
Furthermore, we evaluate three potential defenses aimed at exploring ways to mitigate security threats posed by adversarial policies, providing constructive recommendations for deploying MARL in competitive environments.
The Risk of Federated Learning to Skew Fine-Tuning Features and Underperform Out-of-Distribution Robustness
To tackle the scarcity and privacy issues associated with domain-specific datasets, the integration of federated learning in conjunction with fine-tuning has emerged as a practical solution.
MEAOD: Model Extraction Attack against Object Detectors
The widespread use of deep learning technology across various industries has made deep neural network models highly valuable and, as a result, attractive targets for potential attackers.
Improving the Robustness of Transformer-based Large Language Models with Dynamic Attention
Extensive experiments demonstrate that dynamic attention significantly mitigates the impact of adversarial attacks, improving up to 33\% better performance than previous methods against widely-used adversarial attacks.
Facial Data Minimization: Shallow Model as Your Privacy Filter
Face recognition service has been used in many fields and brings much convenience to people.
TextDefense: Adversarial Text Detection based on Word Importance Entropy
TextDefense differs from previous approaches, where it utilizes the target model for detection and thus is attack type agnostic.
Hijack Vertical Federated Learning Models As One Party
Vertical federated learning (VFL) is an emerging paradigm that enables collaborators to build machine learning models together in a distributed fashion.
"Is your explanation stable?": A Robustness Evaluation Framework for Feature Attribution
Experiment results show that the MeTFA-smoothed explanation can significantly increase the robust faithfulness.
