most citedRethinking the Reverse-engineering of Trojan Triggers

19 citations · 26 across the 5 of their papers we have counts for

collaborators

5 papers

cs.LG2024

Speculative Coreset Selection for Task-Specific Fine-tuning

Xiaoyu Zhang, Juan Zhai, Shiqing Ma +4

Task-specific fine-tuning is essential for the deployment of large language models (LLMs), but it requires significant computational resources and time. Existing solutions have pro…

cs.CL2024

Data-centric NLP Backdoor Defense from the Lens of Memorization

Zhenting Wang, Zhizhi Wang, Mingyu Jin +3

Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample…

cs.CR202219 cited

Rethinking the Reverse-engineering of Trojan Triggers

Zhenting Wang, Kai Mei, Hailun Ding +2

Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-eng…

cs.CV20223 cited

BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning

Zhenting Wang, Juan Zhai, Shiqing Ma

Deep neural networks are vulnerable to Trojan attacks. Existing attacks use visible patterns (e.g., a patch or image transformations) as triggers, which are vulnerable to human ins…

cs.LG20224 cited

FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons

Xuanqi Gao, Juan Zhai, Shiqing Ma +3

With Deep Neural Network (DNN) being integrated into a growing number of critical systems with far-reaching impacts on society, there are increasing concerns on their ethical perfo…