mlsanityData to 14 Oct 2026

Adversarial robustness and RL in finance

356 papers1 this weekLow confidence in this grouping: the papers may belong to more than one topic, or the group may changeLow confidence in this grouping: the papers may belong to more than one topic, or the group may change · About

Keywords: market, adversarial, reinforcement, reinforcement learning, attacks

Key facts. Adversarial robustness and RL in finance: 356 papers on arXiv since 2024 (data through 14 Oct 2026). 11 of its 356 mapped papers (3%) cite “SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents” (2024, arXiv 2405.20539). 11 new papers 30 Sep–14 Oct.

What’s new

30 Sep – 14 Oct 2026

11 new papers, 30 Sep – 14 Oct; 1 this week.

  1. This week · 1
  2. Reinforcement Learning with Hawkes-Structured Networks for Market Making
  3. Earlier · 10
  4. Equal-information evaluation of credit assignment in modular financial reinforcement learning
  5. When to Intervene? State-Aware Sparse Manipulation in Federated Reinforcement Learning
  6. SOTA: Stock Options Trading Agents Guided by Option-Implied Return Distributions
  7. BluffJAX: Adversarial Imperfect Information Games in JAX
  8. Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning
  9. Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning also fits: RL theory and sample complexity
  10. When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader Game
  11. Homomorphic Advantage Operator: Stabilizing Reinforcement Learning Under Fully Homomorphic Encryption Constraints also fits: RL theory and sample complexity
  12. PPO-HRAP: Proximal Policy Optimization with a Hybrid Regime-Aware Policy for Risk-Controlled Trading
All 11
  1. Beyond Supra-Competitive Outcomes: Collusive Behaviour in Deep Reinforcement Learning for Optimal Execution Games

Foundations

Most cited by papers here

  1. SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents2024cited by 11 here
  2. Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategy2025cited by 10 here
  3. Autonomous Network Defence using Reinforcement Learning2024cited by 9 here
  4. Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey2024cited by 8 here
  5. Adversarial Inception Backdoor Attacks against Reinforcement Learning2024cited by 7 here

Lineage

The papers this direction builds on, oldest first.

  1. 2024Discovering Command and Control Channels Using Reinforcement Learningcited by 3 here
  2. 2024CNN-DRL with Shuffled Features in Financecited by 3 here
  3. 2024Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-errorcited by 4 here
  4. 2024Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policiescited by 4 here
  5. 2024Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimizationcited by 3 here
  6. 2024Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Surveycited by 8 here
  7. 2024Reinforcement learningcited by 11 here
  8. 2024Diffusion for World Modeling: Visual Details Matter in Ataricited by 3 here
  9. 2024Reinforcement Learning for Jump-Diffusions, with Financial Applicationscited by 3 here
  10. 2024SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agentscited by 11 here
  11. 2024Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agentscited by 3 here
  12. 2024Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learningcited by 3 here
12 more
  1. 2024Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Spacecited by 3 here
  2. 2024Gymnasium: A Standard Interface for Reinforcement Learning Environmentscited by 13 here
  3. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 7 here
  4. 2024Introduction to Reinforcement Learningcited by 4 here
  5. 2024The Evolution of Reinforcement Learning in Quantitative Finance: A Surveycited by 6 here
  6. 2024Autonomous Network Defence using Reinforcement Learningcited by 9 here
  7. 2024Adversarial Inception Backdoor Attacks against Reinforcement Learningcited by 7 here
  8. 2024CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agentscited by 4 here
  9. 2024Entity-based Reinforcement Learning for Autonomous Cyber Defencecited by 4 here
  10. 2024APIRL: Deep Reinforcement Learning for REST API Fuzzingcited by 3 here
  11. 2025UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learningcited by 3 here
  12. 2025Deep Reinforcement Learning for Automated Stock Trading: An Ensemble Strategycited by 10 here

The 24 most cited of 183.

Browse

30 of 356, ranked 6–35

  1. 6The Evolution of Reinforcement Learning in Quantitative Finance: A Survey20246
  2. 7Towards Optimal Adversarial Robust Q-learning with Bellman Infinity-error20244
  3. 8Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies20244
  4. 9CybORG++: An Enhanced Gym for the Development of Autonomous Cyber Agents20244
  5. 10Entity-based Reinforcement Learning for Autonomous Cyber Defence20244
  6. 11UNIDOOR: A Universal Framework for Action-Level Backdoor Attacks in Deep Reinforcement Learning20253
  7. 12Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learning20253
  8. 13Discovering Command and Control Channels Using Reinforcement Learning20243
  9. 14CNN-DRL with Shuffled Features in Finance20243
  10. 15Combining Transformer based Deep Reinforcement Learning with Black-Litterman Model for Portfolio Optimization20243
All 30
  1. 16Reinforcement Learning for Jump-Diffusions, with Financial Applications20243
  2. 17Breaking the Barrier: Enhanced Utility and Robustness in Smoothed DRL Agents20243
  3. 18Optimizing Cyber Defense in Dynamic Active Directories through Reinforcement Learning20243
  4. 19Mitigating Deep Reinforcement Learning Backdoors in the Neural Activation Space20243
  5. 20Beyond Rewards in Reinforcement Learning for Cyber Defence20262
  6. 21SoK: The Pitfalls of Deep Reinforcement Learning for Cybersecurity20262
  7. 22Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective20252
  8. 23Deep Reinforcement Learning Algorithms for Option Hedging20252
  9. 24Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach20252
  10. 25Interpreting Agent Behaviors in Reinforcement-Learning-Based Cyber-Battle Simulation Platforms20252
  11. 26DRMD: Deep Reinforcement Learning for Malware Detection under Concept Drift20252
  12. 27FinXplore: An Adaptive Deep Reinforcement Learning Framework for Balancing and Discovering Investment Opportunities20252
  13. 28Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents20252
  14. 29Deep Hedging with Market Impact20242
  15. 30AttackGNN: Red-Teaming GNNs in Hardware Security Using Reinforcement Learning20242
  16. 31Advancing Investment Frontiers: Industry-grade Deep Reinforcement Learning for Portfolio Optimization20242
  17. 32Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations20242
  18. 33Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space20242
  19. 34On Minimizing Adversarial Counterfactual Error in Adversarial RL20242
  20. 35Structural Generalization in Autonomous Cyber Incident Response with Message-Passing Neural Networks and Reinforcement Learning20242