Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents

• URL: http://arxiv.org/abs/2309.14615v1
• Date: Tue, 26 Sep 2023 02:07:26 GMT
• Title: Gray-box Adversarial Attack of Deep Reinforcement Learning-based Trading Agents
• Authors: Foozhan Ataiefard, Hadi Hemmati
• Abstract summary: "gray-box" approach for attacking a Deep RL-based trading agent is possible by trading in the same stock market, with no extra access to the trading agent. An adversary agent uses a hybrid Deep Neural Network as its policy consisting of Convolutional layers and fully-connected layers.
• Score: 0.8339831319589133
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, deep reinforcement learning (Deep RL) has been successfully implemented as a smart agent in many systems such as complex games, self-driving cars, and chat-bots. One of the interesting use cases of Deep RL is its application as an automated stock trading agent. In general, any automated trading agent is prone to manipulations by adversaries in the trading environment. Thus studying their robustness is vital for their success in practice. However, typical mechanism to study RL robustness, which is based on white-box gradient-based adversarial sample generation techniques (like FGSM), is obsolete for this use case, since the models are protected behind secure international exchange APIs, such as NASDAQ. In this research, we demonstrate that a "gray-box" approach for attacking a Deep RL-based trading agent is possible by trading in the same stock market, with no extra access to the trading agent. In our proposed approach, an adversary agent uses a hybrid Deep Neural Network as its policy consisting of Convolutional layers and fully-connected layers. On average, over three simulated trading market configurations, the adversary policy proposed in this research is able to reduce the reward values by 214.17%, which results in reducing the potential profits of the baseline by 139.4%, ensemble method by 93.7%, and an automated trading software developed by our industrial partner by 85.5%, while consuming significantly less budget than the victims (427.77%, 187.16%, and 66.97%, respectively).

Related papers

• When AI Trading Agents Compete: Adverse Selection of Meta-Orders by Reinforcement Learning-Based Market Making [0.061173711613792085]
  We investigate the mechanisms by which medium-frequency trading agents are adversely selected by opportunistic high-frequency traders.<n>We use reinforcement learning (RL) within a Hawkes Limit Order Book (LOB) model in order to replicate the behaviours of high-frequency market makers.
  arXiv  Detail & Related papers  (2025-10-31T10:05:14Z)
• Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition [101.86739402748995]
  We run the largest public red-teaming competition to date, targeting 22 frontier AI agents across 44 realistic deployment scenarios.<n>We build the Agent Red Teaming benchmark and evaluate it across 19 state-of-the-art models.<n>Our findings highlight critical and persistent vulnerabilities in today's AI agents.
  arXiv  Detail & Related papers  (2025-07-28T05:13:04Z)
• HedgeAgents: A Balanced-aware Multi-agent Financial Trading System [20.48571388047213]
  Large Language Models (LLMs) and Agent-based models exhibit promising potential in real-time market analysis and trading decisions. They still experience a significant -20% loss when confronted with rapid declines or frequent fluctuations. This paper introduces an innovative multi-agent system, HedgeAgents, aimed at bolstering system via hedging robustness'' strategies.
  arXiv  Detail & Related papers  (2025-02-17T04:13:19Z)
• Self-Regulation and Requesting Interventions [63.5863047447313]
  We propose an offline framework that trains a "helper" policy to request interventions. We score optimal intervention timing with PRMs and train the helper model on these labeled trajectories. This offline approach significantly reduces costly intervention calls during training.
  arXiv  Detail & Related papers  (2025-02-07T00:06:17Z)
• Hierarchical Reinforced Trader (HRT): A Bi-Level Approach for Optimizing Stock Selection and Execution [0.9553307596675155]
  We introduce the Hierarchical Reinforced Trader (HRT), a novel trading strategy employing a bi-level Hierarchical Reinforcement Learning framework. HRT integrates a Proximal Policy Optimization (PPO)-based High-Level Controller (HLC) for strategic stock selection with a Deep Deterministic Policy Gradient (DDPG)-based Low-Level Controller (LLC) tasked with optimizing trade executions to enhance portfolio value.
  arXiv  Detail & Related papers  (2024-10-19T01:29:38Z)
• Improved Generation of Adversarial Examples Against Safety-aligned LLMs [72.38072942860309]
  Adversarial prompts generated using gradient-based methods exhibit outstanding performance in performing automatic jailbreak attacks against safety-aligned LLMs. In this paper, we explore a new perspective on this problem, suggesting that it can be alleviated by leveraging innovations inspired in transfer-based attacks. We show that 87% of the query-specific adversarial suffixes generated by the developed combination can induce Llama-2-7B-Chat to produce the output that exactly matches the target string on AdvBench.
  arXiv  Detail & Related papers  (2024-05-28T06:10:12Z)
• Fault Injection and Safe-Error Attack for Extraction of Embedded Neural Network Models [1.2499537119440245]
  We focus on embedded deep neural network models on 32-bit microcontrollers in the Internet of Things (IoT) We propose a black-box approach to craft a successful attack set. For a classical convolutional neural network, we successfully recover at least 90% of the most significant bits with about 1500 crafted inputs.
  arXiv  Detail & Related papers  (2023-08-31T13:09:33Z)
• G$^2$uardFL: Safeguarding Federated Learning Against Backdoor Attacks through Attributed Client Graph Clustering [116.4277292854053]
  Federated Learning (FL) offers collaborative model training without data sharing. FL is vulnerable to backdoor attacks, where poisoned model weights lead to compromised system integrity. We present G$2$uardFL, a protective framework that reinterprets the identification of malicious clients as an attributed graph clustering problem.
  arXiv  Detail & Related papers  (2023-06-08T07:15:04Z)
• A Novel Deep Reinforcement Learning Based Automated Stock Trading System Using Cascaded LSTM Networks [3.593955557310285]
  We propose a DRL based stock trading system using cascaded LSTM, which first uses LSTM to extract the time-series features from stock daily data, and then the features extracted are fed to the agent for training. Experiments in DJI in the US market and SSE50 in the Chinese stock market show that our model outperforms previous baseline models in terms of cumulative returns and Sharp ratio.
  arXiv  Detail & Related papers  (2022-12-06T03:22:06Z)
• Deep Reinforcement Learning in Quantitative Algorithmic Trading: A Review [0.0]
  Deep Reinforcement Learning agents proved to be to a force to be reckon with in many games like Chess and Go. This paper reviews the progress made so far with deep reinforcement learning in the subdomain of AI in finance. We conclude that DRL in stock trading has showed huge applicability potential rivalling professional traders under strong assumptions.
  arXiv  Detail & Related papers  (2021-05-31T22:26:43Z)
• BACKDOORL: Backdoor Attack against Competitive Reinforcement Learning [80.99426477001619]
  We migrate backdoor attacks to more complex RL systems involving multiple agents. As a proof of concept, we demonstrate that an adversary agent can trigger the backdoor of the victim agent with its own action. The results show that when the backdoor is activated, the winning rate of the victim drops by 17% to 37% compared to when not activated.
  arXiv  Detail & Related papers  (2021-05-02T23:47:55Z)
• Adversarial Attacks on Deep Algorithmic Trading Policies [8.774604259603302]
  Deep Reinforcement Learning (DRL) has become an appealing solution to algorithmic trading such as high frequency trading of stocks and cyptocurrencies. It follows that algorithmic trading DRL agents may also be compromised by such adversarial techniques, leading to policy manipulation. We develop a threat model for deep trading policies, and propose two attack techniques for manipulating the performance of such policies at test-time.
  arXiv  Detail & Related papers  (2020-10-22T02:26:29Z)
• Robust Deep Reinforcement Learning through Adversarial Loss [74.20501663956604]
  Recent studies have shown that deep reinforcement learning agents are vulnerable to small adversarial perturbations on the agent's inputs. We propose RADIAL-RL, a principled framework to train reinforcement learning agents with improved robustness against adversarial attacks.
  arXiv  Detail & Related papers  (2020-08-05T07:49:42Z)
• Scalable Multi-Agent Inverse Reinforcement Learning via Actor-Attention-Critic [54.2180984002807]
  Multi-agent adversarial inverse reinforcement learning (MA-AIRL) is a recent approach that applies single-agent AIRL to multi-agent problems. We propose a multi-agent inverse RL algorithm that is more sample-efficient and scalable than previous works.
  arXiv  Detail & Related papers  (2020-02-24T20:30:45Z)
• Adversarial Attacks on Machine Learning Systems for High-Frequency Trading [55.30403936506338]
  We study valuation models for algorithmic trading from the perspective of adversarial machine learning. We introduce new attacks specific to this domain with size constraints that minimize attack costs. We discuss how these attacks can be used as an analysis tool to study and evaluate the robustness properties of financial models.
  arXiv  Detail & Related papers  (2020-02-21T22:04:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.