paper-with-me

홈 › Papers

Topological Detection of Trojaned Neural Networks

2021-06-11 · NeurIPS 2021 12 · Songzhu Zheng, Yikai Zhang, Hubert Wagner, Mayank Goswami, Chao Chen

Deep neural networks are known to have security issues. One particular threat is the Trojan attack. It occurs when the attackers stealthily manipulate the model's behavior through Trojaned training samples, which can later be exploited. Guided by basic neuroscientific principles we discover subtle -- yet critical -- structural deviation characterizing Trojaned models. In our analysis we use topological tools. They allow us to model high-order dependencies in the networks, robustly compare different networks, and localize structural abnormalities. One interesting observation is that Trojaned models develop short-cuts from input to output layers. Inspired by these observations, we devise a strategy for robust detection of Trojaned models. Compared to standard baselines it displays better performance on multiple benchmarks.

📄 PDF Abstract BibTeX arXiv:2106.06469

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Trigger Hunting with a Topological Prior for Trojan Detection

2021-10-15 · ICLR 2022 4 · Xiaoling Hu, Xiao Lin, Michael Cogswell, Yi Yao 외

Despite their success and popularity, deep neural networks (DNNs) are vulnerable when facing backdoor attacks. This impedes their wider adoption, especially in mission critical applications. This paper tackles the proble…

Diversity

On Trojan Signatures in Large Language Models of Code

2024-02-23 · Aftab Hussain, Md Rafiqul Islam Rabin, Mohammad Amin Alipour

Trojan signatures, as described by Fields et al. (2021), are noticeable differences in the distribution of the trojaned class parameters (weights) and the non-trojaned class parameters of the trojaned model, that can be …

Binary ClassificationDefect Detection

Cassandra: Detecting Trojaned Networks from Adversarial Perturbations

2020-07-28 · Xiao-Yu Zhang, Ajmal Mian, Rohit Gupta, Nazanin Rahnavard 외

Deep neural networks are being widely deployed for many critical tasks due to their high classification accuracy. In many cases, pre-trained models are sourced from vendors who may have disrupted the training pipeline to…

Adversarial DefenseAnomaly Detection

Dormant Neural Trojans

2022-11-02 · Feisi Fu, Panagiota Kiourti, Wenchao Li

We present a novel methodology for neural network backdoor attacks. Unlike existing training-time attacks where the Trojaned network would respond to the Trojan trigger after training, our approach inserts a Trojan that …

The TrojAI Software Framework: An OpenSource tool for Embedding Trojans into Deep Learning Models

2020-03-13 · Kiran Karra, Chace Ashcraft, Neil Fendley

In this paper, we introduce the TrojAI software framework, an open source set of Python tools capable of generating triggered (poisoned) datasets and associated deep learning (DL) models with trojans at scale. We utilize…

Reinforcement Learning