# Adversarial Machine Learning Attacks on Financial Reporting via Maximum Violated Multi-Objective Attack

arXiv: https://arxiv.org/abs/2507.05441 · HTML: https://mlsanity.com/paper/2507.05441/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 70 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 24 of 24)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning](https://mlsanity.com/paper/1712.03141/) (2017)
- [Efficient and Modular Implicit Differentiation](https://mlsanity.com/paper/2105.15183/) (2021)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [Security Evaluation of Pattern Classifiers under Attack](https://mlsanity.com/paper/1709.00609/) (2017)
- [Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descent](https://mlsanity.com/paper/2106.15023/) (2021)
- [Overparameterized Linear Regression under Adversarial Attacks](https://mlsanity.com/paper/2204.06274/) (2022)
- [Adversarial Attacks, Regression, and Numerical Stability Regularization](https://mlsanity.com/paper/1812.02885/) (2018)
- [Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theory](https://mlsanity.com/paper/1911.04636/) (2019)
- [Adversarial Purification with the Manifold Hypothesis](https://mlsanity.com/paper/2210.14404/) (2022)
- [Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations](https://mlsanity.com/paper/2310.19978/) (2023)
- [SoK: A Review of Differentially Private Linear Models For High-Dimensional Data](https://mlsanity.com/paper/2404.01141/) (2024)
- [Improving Fast Minimum-Norm Attacks with Hyperparameter Optimization](https://mlsanity.com/paper/2310.08177/) (2023)
- [Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling](https://mlsanity.com/paper/2410.23601/) (2024)
- [You Don't Need Robust Machine Learning to Manage Adversarial Attack Risks](https://mlsanity.com/paper/2306.09951/) (2023)
- [Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Context](https://mlsanity.com/paper/2412.16359/) (2024)
- [Generating Adversarial Examples with Task Oriented Multi-Objective Optimization](https://mlsanity.com/paper/2304.13229/) (2023)
- [Differentially Private Iterative Screening Rules for Linear Regression](https://mlsanity.com/paper/2502.18578/) (2025)
- [Stop Walking in Circles! Bailing Out Early in Projected Gradient Descent](https://mlsanity.com/paper/2503.19347/) (2025)
- [More Options for Prelabor Rupture of Membranes, A Bayesian Analysis](https://mlsanity.com/paper/2408.10876/) (2024)

## Built on by (most cited first, 1 of 1)

- [Adversarial Samples Are Not Created Equal](https://mlsanity.com/paper/2601.00577/) (2026)

## Abstract (arXiv)

Bad actors, primarily distressed firms, have the incentive and desire to manipulate their financial reports to hide their distress and derive personal gains. As attackers, these firms are motivated by potentially millions of dollars and the availability of many publicly disclosed and used financial modeling frameworks. Existing attack methods do not work on this data due to anti-correlated objectives that must both be satisfied for the attacker to succeed. We introduce Maximum Violated Multi-Objective (MVMO) attacks that adapt the attacker's search direction to find 20× more satisfying attacks compared to standard attacks. The result is that in ≈50% of cases, a company could inflate their earnings by 100-200%, while simultaneously reducing their fraud scores by 15%. By working with lawyers and professional accountants, we ensure our threat model is realistic to how such frauds are performed in practice.