# The Effect of Class Definitions on the Transferability of Adversarial Attacks Against Forensic CNNs

arXiv: https://arxiv.org/abs/2101.11081 · HTML: https://mlsanity.com/paper/2101.11081/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 26 Jan 2021.

## Builds on (most cited first, 15 of 15)

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [DeepFool: a simple and accurate method to fool deep neural networks](https://mlsanity.com/paper/1511.04599/) (2015)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Evasion Attacks against Machine Learning at Test Time](https://mlsanity.com/paper/1708.06131/) (2017)
- [Delving into Transferable Adversarial Examples and Black-box Attacks](https://mlsanity.com/paper/1611.02770/) (2016)
- [Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples](https://mlsanity.com/paper/1605.07277/) (2016)
- [Adversarial Attacks on Neural Network Policies](https://mlsanity.com/paper/1702.02284/) (2017)
- [Noiseprint: a CNN-based camera model fingerprint](https://mlsanity.com/paper/1808.08396/) (2018)
- [Forensic Similarity for Digital Images](https://mlsanity.com/paper/1902.04684/) (2019)
- [On the Transferability of Adversarial Examples Against CNN-Based Image Forensics](https://mlsanity.com/paper/1811.01629/) (2018)
- [A Counter-Forensic Method for CNN-Based Camera Model Identification](https://mlsanity.com/paper/1805.02131/) (2018)

## Built on by (most cited first, 3 of 3)

- [Making DeepFakes more spurious: evading deep face forgery detection via trace removal attack](https://mlsanity.com/paper/2203.11433/) (2022)
- [Making Generated Images Hard To Spot: A Transferable Attack On Synthetic Image Detectors](https://mlsanity.com/paper/2104.12069/) (2021)
- [Frequency Bias Matters: Diving into Robust and Generalized Deep Image Forgery Detection](https://mlsanity.com/paper/2511.19886/) (2025)

## Abstract (arXiv)

In recent years, convolutional neural networks (CNNs) have been widely used by researchers to perform forensic tasks such as image tampering detection. At the same time, adversarial attacks have been developed that are capable of fooling CNN-based classifiers. Understanding the transferability of adversarial attacks, i.e. an attacks ability to attack a different CNN than the one it was trained against, has important implications for designing CNNs that are resistant to attacks. While attacks on object recognition CNNs are believed to be transferrable, recent work by Barni et al. has shown that attacks on forensic CNNs have difficulty transferring to other CNN architectures or CNNs trained using different datasets. In this paper, we demonstrate that adversarial attacks on forensic CNNs are even less transferrable than previously thought even between virtually identical CNN architectures! We show that several common adversarial attacks against CNNs trained to identify image manipulation fail to transfer to CNNs whose only difference is in the class definitions (i.e. the same CNN architectures trained using the same data). We note that all formulations of class definitions contain the unaltered class. This has important implications for the future design of forensic CNNs that are robust to adversarial and anti-forensic attacks.