mlsanityData to 7 Oct 2026

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

arXiv 2507.05441 ↗First posted 7 Jul 2025cs.LG stat.MLcited by 1

Not on the map. Why?

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.

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

Builds on

24 of 70 references.

References · 24

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  2. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  3. 2020Extracting Training Data from Large Language Modelscited by 2,144
  4. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  5. 2017Wild Patterns: Ten Years After the Rise of Adversarial Machine Learningcited by 411
  6. 2021Efficient and Modular Implicit Differentiationcited by 199
  7. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 123
  8. 2022"Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practicecited by 55
  9. 2017Security Evaluation of Pattern Classifiers under Attackcited by 39
  10. 2021Evading Adversarial Example Detection Defenses with Orthogonal Projected Gradient Descentcited by 34
  11. 2022Overparameterized Linear Regression under Adversarial Attackscited by 21
  12. 2018Adversarial Attacks, Regression, and Numerical Stability Regularizationcited by 14
12 more
  1. 2019Robust Design of Deep Neural Networks against Adversarial Attacks based on Lyapunov Theorycited by 13
  2. 2022Adversarial Purification with the Manifold Hypothesiscited by 8
  3. 2023Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterationscited by 8
  4. 2024SoK: A Review of Differentially Private Linear Models For High-Dimensional Datacited by 5
  5. 2023Improving Fast Minimum-Norm Attacks with Hyperparameter Optimizationcited by 4
  6. 2024Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Samplingcited by 4
  7. 2023You Don't Need Robust Machine Learning to Manage Adversarial Attack Riskscited by 3
  8. 2024Human-Readable Adversarial Prompts: An Investigation into LLM Vulnerabilities Using Situational Contextcited by 3
  9. 2023Generating Adversarial Examples with Task Oriented Multi-Objective Optimizationcited by 2
  10. 2025Differentially Private Iterative Screening Rules for Linear Regressioncited by 2
  11. 2025Stop Walking in Circles! Bailing Out Early in Projected Gradient Descentcited by 2
  12. 2024More Options for Prelabor Rupture of Membranes, A Bayesian Analysiscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Adversarial Samples Are Not Created Equalcited by 0