Search Results for author:
Found 4 papers, 0 papers with code
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.
Efficient and Low Overhead Website Fingerprinting Attacks and Defenses based on TCP/IP Traffic
To achieve a configurable trade-off between the defense and the network overhead, we further improve the list-based defense by a traffic splitting mechanism, which can combat the mentioned attacks as well as save a considerable amount of network overhead.
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.
ABG: A Multi-Party Mixed Protocol Framework for Privacy-Preserving Cooperative Learning
To address the issue of privacy-preserving in collaborative learning, secure outsourced computation and federated learning are two typical methods.
