Lune

CVPR2020Top-tier venue

Universal Litmus Patterns: Revealing Backdoor Attacks in CNNs

Soheil Kolouri, Aniruddha Saha, Hamed Pirsiavash, Heiko Hoffmann

Abstract

The unprecedented success of deep neural networks in many applications has made these networks a prime target for adversarial exploitation. In this paper, we introduce a benchmark technique for detecting backdoor attacks (aka Trojan attacks) on deep convolutional neural networks (CNNs). We introduce the concept of Universal Litmus Patterns (ULPs), which enable one to reveal backdoor attacks by feeding these universal patterns to the network and analyzing the output (i.e., classifying the network as 'clean' or 'corrupted'). This detection is fast because it requires only a few forward passes through a CNN. We demonstrate the effectiveness of ULPs for detecting backdoor attacks on thousands of networks with different architectures trained on four benchmark datasets, namely the German Traffic Sign Recognition Benchmark (GTSRB), MNIST, CIFAR10, and Tiny-ImageNet. The codes and train/test models for this paper can be found here: https://umbcvision . github.io/Universal-Litmus-Patterns/.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

77 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Backdoor Scanning for Deep Neural Networks through K-Arm Optimization cites Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
  • Backdoor Scanning for Deep Neural Networks through K-Arm Optimization cites Trojaning Attack on Neural Networks
  • Backdoor Scanning for Deep Neural Networks through K-Arm Optimization cites Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
  • Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification cites Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
  • Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks cites Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
  • Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks cites Trojaning Attack on Neural Networks
  • Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks cites Towards Evaluating the Robustness of Neural Networks
  • When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks cites Trojaning Attack on Neural Networks
  • When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning Attacks cites Towards Evaluating the Robustness of Neural Networks
  • Black-box Detection of Backdoor Attacks with Limited Information and Data cites Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
  • Black-box Detection of Backdoor Attacks with Limited Information and Data cites Trojaning Attack on Neural Networks
  • Black-box Detection of Backdoor Attacks with Limited Information and Data cites Towards Evaluating the Robustness of Neural Networks
  • Anti-Backdoor Learning: Training Clean Models on Poisoned Data cites Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
  • Anti-Backdoor Learning: Training Clean Models on Poisoned Data cites Trojaning Attack on Neural Networks
  • Anti-Backdoor Learning: Training Clean Models on Poisoned Data cites Backdoor Scanning for Deep Neural Networks through K-Arm Optimization
  • Anti-Backdoor Learning: Training Clean Models on Poisoned Data cites Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification
  • Anti-Backdoor Learning: Training Clean Models on Poisoned Data cites Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers77

  1. Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural NetworksYige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu et al.ICLR 2021 · 548 citations
  2. Anti-Backdoor Learning: Training Clean Models on Poisoned DataYige Li, Xixiang Lyu, Nodens Koren, Lingjuan Lyu et al.NeurIPS 2021 · 503 citations
  3. Deep Feature Space Trojan Attack of Neural Networks by Controlled DetoxificationSiyuan Cheng, Yingqi Liu, Shiqing Ma, Xiangyu ZhangAAAI 2021 · 191 citations
  4. Backdoor Scanning for Deep Neural Networks through K-Arm OptimizationGuangyu Shen, Yingqi Liu, Guanhong Tao, Shengwei An et al.ICML 2021 · 137 citations
  5. Black-box Detection of Backdoor Attacks with Limited Information and DataYinpeng Dong, Xiao Yang, Zhijie Deng, Tianyu Pang et al.ICCV 2021 · 128 citations

Builds on4

  1. Towards Evaluating the Robustness of Neural NetworksNicholas Carlini, David A. WagnerS&P 2017 · 9,786 citations
  2. Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural NetworksBolun Wang, Yuanshun Yao, Shawn Shan, Huiying Li et al.S&P 2019 · 1,801 citations
  3. Trojaning Attack on Neural NetworksYingqi Liu, Shiqing Ma, Yousra Aafer, Wen-Chuan Lee et al.NDSS 2018 · 1,377 citations
  4. When Does Machine Learning FAIL? Generalized Transferability for Evasion and Poisoning AttacksOctavian Suciu, Radu Marginean, Yigitcan Kaya, Hal Daumé III et al.USENIX Security 2018 · 321 citations

Related papers

  1. Beating Backdoor Attack at Its Own GameMin Liu, Alberto L. Sangiovanni-Vincentelli, Xiangyu YueICCV 2023 · 19 citations
  2. AdvDoor: adversarial backdoor attack of deep learning systemQuan Zhang, Yifeng Ding, Yongqiang Tian, Jianmin Guo et al.ISSTA 2021 · 57 citations
  3. UMD: Unsupervised Model Detection for X2X Backdoor AttacksZhen Xiang, Zidi Xiong, Bo LiICML 2023 · 27 citations
  4. FreeEagle: Detecting Complex Neural Trojans in Data-Free CasesChong Fu, Xuhong Zhang, Shouling Ji, Ting Wang et al.USENIX Security 2023
  5. ABS: Scanning Neural Networks for Back-doors by Artificial Brain StimulationYingqi Liu, Wen-Chuan Lee, Guanhong Tao, Shiqing Ma et al.CCS 2019 · 531 citations
Dusk over the sea between two cliffs drawn in fine vertical lines