Lujia Shen (Zhejiang University), Yuwen Pu (Zhejiang University), Shouling Ji (Zhejiang University), Changjiang Li (Penn State), Xuhong Zhang (Zhejiang University), Chunpeng Ge (Shandong University), Ting Wang (Penn State)

Transformer-based models, such as BERT and GPT, have been widely adopted in natural language processing (NLP) due to their exceptional performance. However, recent studies show their vulnerability to textual adversarial attacks where the model's output can be misled by intentionally manipulating the text inputs. Despite various methods that have been proposed to enhance the model's robustness and mitigate this vulnerability, many require heavy consumption resources (e.g., adversarial training) or only provide limited protection (e.g., defensive dropout).

In this paper, we propose a novel method called dynamic attention, tailored for the transformer architecture, to enhance the inherent robustness of the model itself against various adversarial attacks. Our method requires no downstream task knowledge and does not incur additional costs. The proposed dynamic attention consists of two modules: *(i) attention rectification*, which masks or weakens the attention value of the chosen tokens, and *(ii) dynamic modeling*, which dynamically builds the set of candidate tokens. Extensive experiments demonstrate that dynamic attention significantly mitigates the impact of adversarial attacks, improving up to 33% compared to previous methods against widely used adversarial attacks. The model-level design of dynamic attention enables it to be easily combined with other defense methods (e.g., adversarial training) to further enhance the model's robustness. Furthermore, we demonstrate that dynamic attention preserves the state-of-the-art robustness space of the original model compared to other dynamic modeling methods.

View More Papers

PANDORA: Jailbreak GPTs by Retrieval Augmented Generation Poisoning

Gelei Deng, Yi Liu (Nanyang Technological University), Yuekang Li (The University of New South Wales), Wang Kailong(Huazhong University of Science and Technology), Tianwei Zhang, Yang Liu (Nanyang Technological University)

Read More

EnclaveFuzz: Finding Vulnerabilities in SGX Applications

Liheng Chen (Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber Security, University of Chinese Academy of Sciences; Institute for Network Science and Cyberspace of Tsinghua University), Zheming Li (Institute for Network Science and Cyberspace of Tsinghua University), Zheyu Ma (Institute for Network Science and Cyberspace of Tsinghua University), Yuan Li (Tsinghua University),…

Read More

WIP: A Trust Assessment Method for In-Vehicular Networks using...

Artur Hermann, Natasa Trkulja (Ulm University - Institute of Distributed Systems), Anderson Ramon Ferraz de Lucena, Alexander Kiening (DENSO AUTOMOTIVE Deutschland GmbH), Ana Petrovska (Huawei Technologies), Frank Kargl (Ulm University - Institute of Distributed Systems)

Read More