mlsanityData to 7 Oct 2026

TESDA: Transform Enabled Statistical Detection of Attacks in Deep Neural Networks

arXiv 2110.08447 ↗First posted 16 Oct 2021cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are now the de facto choice for computer vision tasks such as image classification. However, their complexity and "black box" nature often renders the systems they're deployed in vulnerable to a range of security threats. Successfully identifying such threats, especially in safety-critical real-world applications is thus of utmost importance, but still very much an open problem. We present TESDA, a low-overhead, flexible, and statistically grounded method for {online detection} of attacks by exploiting the discrepancies they cause in the distributions of intermediate layer features of DNNs. Unlike most prior work, we require neither dedicated hardware to run in real-time, nor the presence of a Trojan trigger to detect discrepancies in behavior. We empirically establish our method's usefulness and practicality across multiple architectures, datasets and diverse attacks, consistently achieving detection coverages of above 95% with operation count overheads as low as 1-2%.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 16 Oct 2021.

Builds on

18 of 42 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  6. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  7. 2019STRIP: A Defence Against Trojan Attacks on Deep Neural Networkscited by 437
  8. 2018Certified Defenses against Adversarial Examplescited by 305
  9. 2020Input-Aware Dynamic Backdoor Attackcited by 304
  10. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  11. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  12. 2017On the (Statistical) Detection of Adversarial Examplescited by 180
6 more
  1. 2014A Tutorial on Principal Component Analysiscited by 139
  2. 2016Technical Report on the CleverHans v2.1.0 Adversarial Examples Librarycited by 123
  3. 2019TBT: Targeted Neural Network Attack with Bit Trojancited by 112
  4. 2020CLEANN: Accelerated Trojan Shield for Embedded Neural Networkscited by 22
  5. 2021Explainable Adversarial Attacks in Deep Neural Networks Using Activation Profilescited by 6
  6. 2015Multivariate Chebyshev Inequality with Estimated Mean and Variancecited by 5

Built on by

Not cited yet.