How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies

• URL: http://arxiv.org/abs/2502.03698v3
• Date: Tue, 14 Oct 2025 02:44:00 GMT
• Title: How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
• Authors: Akansha Kalra, Basavasagar Patil, Guanhong Tao, Daniel S. Brown,
• Abstract summary: Learning from Demonstration (LfD) algorithms have shown promising results in robotic manipulation tasks.<n>But their vulnerability to offline universal perturbation attacks remains underexplored.<n>This paper presents a comprehensive study of adversarial attacks on both classic and recently proposed algorithms.
• Score: 15.999261636389702
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Learning from Demonstration (LfD) algorithms have shown promising results in robotic manipulation tasks, but their vulnerability to offline universal perturbation attacks remains underexplored. This paper presents a comprehensive study of adversarial attacks on both classic and recently proposed algorithms, including Behavior Cloning (BC), LSTM-GMM, Implicit Behavior Cloning (IBC), Diffusion Policy (DP), and Vector-Quantizied Behavior Transformer (VQ-BET). We study the vulnerability of these methods to universal adversarial perturbations. Our experiments on several simulated robotic manipulation tasks reveal that most of the current methods are highly vulnerable to adversarial perturbations. We also show that these attacks are often transferable across algorithms, architectures, and tasks, raising concerning security vulnerabilities to black-box attacks. To the best of our knowledge, we are the first to present a systematic study of the vulnerabilities of different LfD algorithms to both white-box and black-box attacks. Our findings highlight the vulnerabilities of modern BC algorithms, paving the way for future work in addressing such limitations.

Related papers

• Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applications [0.21485350418225244]
  Explainable Artificial Intelligence (XAI) has aided machine learning (ML) researchers with the power of scrutinizing the decisions of the black-box models.<n>XAI methods can themselves be a victim of post-adversarial attacks that manipulate the expected outcome from the explanation module.
  arXiv  Detail & Related papers  (2025-10-04T02:07:58Z)
• Algorithms for Adversarially Robust Deep Learning [58.656107500646364]
  We discuss recent progress toward designing algorithms that exhibit desirable robustness properties.<n>We present new algorithms that achieve state-of-the-art generalization in medical imaging, molecular identification, and image classification.<n>We propose new attacks and defenses, which represent the frontier of progress toward designing robust language-based agents.
  arXiv  Detail & Related papers  (2025-09-23T14:48:58Z)
• Quantifying Loss Aversion in Cyber Adversaries via LLM Analysis [2.798191832420146]
  IARPA's ReSCIND program seeks to infer, defend against, and exploit attacker cognitive traits.<n>In this paper, we present a novel methodology that leverages large language models (LLMs) to extract quantifiable insights into the cognitive bias of loss aversion from hacker behavior.
  arXiv  Detail & Related papers  (2025-08-18T05:51:30Z)
• Constrained Black-Box Attacks Against Multi-Agent Reinforcement Learning [8.080255323094079]
  Collaborative multi-agent reinforcement learning (c-MARL) has rapidly evolved, offering state-of-the-art algorithms for real-world applications.<n>However, a key challenge to its widespread adoption is the lack of a thorough investigation into its vulnerabilities to adversarial attacks.<n>This paper investigates new vulnerabilities under more realistic and constrained conditions, assuming an adversary can only collect and perturb the observations of deployed agents.
  arXiv  Detail & Related papers  (2025-08-12T18:31:15Z)
• Toward Spiking Neural Network Local Learning Modules Resistant to Adversarial Attacks [2.3312335998006306]
  Recent research has shown the vulnerability of Spiking Neural Networks (SNNs) under adversarial examples. We introduce a hybrid adversarial attack paradigm that leverages the transferability of adversarial instances. The proposed hybrid approach demonstrates superior performance, outperforming existing adversarial attack methods.
  arXiv  Detail & Related papers  (2025-04-11T18:07:59Z)
• Robust Intrusion Detection System with Explainable Artificial Intelligence [0.0]
  Adversarial input can exploit machine learning (ML) models through standard interfaces. Conventional defenses such as adversarial training are costly in computational terms and often fail to provide real-time detection. We suggest a novel strategy for detecting and mitigating adversarial attacks using eXplainable Artificial Intelligence (XAI)
  arXiv  Detail & Related papers  (2025-03-07T10:31:59Z)
• MirrorCheck: Efficient Adversarial Defense for Vision-Language Models [55.73581212134293]
  We propose a novel, yet elegantly simple approach for detecting adversarial samples in Vision-Language Models. Our method leverages Text-to-Image (T2I) models to generate images based on captions produced by target VLMs. Empirical evaluations conducted on different datasets validate the efficacy of our approach.
  arXiv  Detail & Related papers  (2024-06-13T15:55:04Z)
• Multi-granular Adversarial Attacks against Black-box Neural Ranking Models [111.58315434849047]
  We create high-quality adversarial examples by incorporating multi-granular perturbations. We transform the multi-granular attack into a sequential decision-making process. Our attack method surpasses prevailing baselines in both attack effectiveness and imperceptibility.
  arXiv  Detail & Related papers  (2024-04-02T02:08:29Z)
• Mutual-modality Adversarial Attack with Semantic Perturbation [81.66172089175346]
  We propose a novel approach that generates adversarial attacks in a mutual-modality optimization scheme. Our approach outperforms state-of-the-art attack methods and can be readily deployed as a plug-and-play solution.
  arXiv  Detail & Related papers  (2023-12-20T05:06:01Z)
• Unveiling Vulnerabilities in Interpretable Deep Learning Systems with Query-Efficient Black-box Attacks [16.13790238416691]
  Interpretable Deep Learning Systems (IDLSes) are designed to make the system more transparent and explainable. We propose a novel microbial genetic algorithm-based black-box attack against IDLSes that requires no prior knowledge of the target model and its interpretation model.
  arXiv  Detail & Related papers  (2023-07-21T21:09:54Z)
• Deep PackGen: A Deep Reinforcement Learning Framework for Adversarial Network Packet Generation [3.5574619538026044]
  Recent advancements in artificial intelligence (AI) and machine learning (ML) algorithms have enhanced the security posture of cybersecurity operations centers (defenders) Recent studies have found that the perturbation of flow-based and packet-based features can deceive ML models, but these approaches have limitations. Our framework, Deep PackGen, employs deep reinforcement learning to generate adversarial packets and aims to overcome the limitations of approaches in the literature.
  arXiv  Detail & Related papers  (2023-05-18T15:32:32Z)
• Toward Evaluating Robustness of Reinforcement Learning with Adversarial Policy [32.1138935956272]
  Reinforcement learning agents are susceptible to evasion attacks during deployment. In this paper, we propose Intrinsically Motivated Adrial Policy (IMAP) for efficient black-box adversarial policy learning.
  arXiv  Detail & Related papers  (2023-05-04T07:24:12Z)
• Adv-Bot: Realistic Adversarial Botnet Attacks against Network Intrusion Detection Systems [0.7829352305480285]
  A growing number of researchers are recently investigating the feasibility of such attacks against machine learning-based security systems. This study was to investigate the actual feasibility of adversarial attacks, specifically evasion attacks, against network-based intrusion detection systems. Our goal is to create adversarial botnet traffic that can avoid detection while still performing all of its intended malicious functionality.
  arXiv  Detail & Related papers  (2023-03-12T14:01:00Z)
• Towards Adversarial Realism and Robust Learning for IoT Intrusion Detection and Classification [0.0]
  The Internet of Things (IoT) faces tremendous security challenges. The increasing threat posed by adversarial attacks restates the need for reliable defense strategies. This work describes the types of constraints required for an adversarial cyber-attack example to be realistic.
  arXiv  Detail & Related papers  (2023-01-30T18:00:28Z)
• Resisting Deep Learning Models Against Adversarial Attack Transferability via Feature Randomization [17.756085566366167]
  We propose a feature randomization-based approach that resists eight adversarial attacks targeting deep learning models. Our methodology can secure the target network and resists adversarial attack transferability by over 60%.
  arXiv  Detail & Related papers  (2022-09-11T20:14:12Z)
• Fixed Points in Cyber Space: Rethinking Optimal Evasion Attacks in the Age of AI-NIDS [70.60975663021952]
  We study blackbox adversarial attacks on network classifiers. We argue that attacker-defender fixed points are themselves general-sum games with complex phase transitions. We show that a continual learning approach is required to study attacker-defender dynamics.
  arXiv  Detail & Related papers  (2021-11-23T23:42:16Z)
• Balancing detectability and performance of attacks on the control channel of Markov Decision Processes [77.66954176188426]
  We investigate the problem of designing optimal stealthy poisoning attacks on the control channel of Markov decision processes (MDPs) This research is motivated by the recent interest of the research community for adversarial and poisoning attacks applied to MDPs, and reinforcement learning (RL) methods.
  arXiv  Detail & Related papers  (2021-09-15T09:13:10Z)
• Policy Smoothing for Provably Robust Reinforcement Learning [109.90239627115336]
  We study the provable robustness of reinforcement learning against norm-bounded adversarial perturbations of the inputs. We generate certificates that guarantee that the total reward obtained by the smoothed policy will not fall below a certain threshold under a norm-bounded adversarial of perturbation the input.
  arXiv  Detail & Related papers  (2021-06-21T21:42:08Z)
• A black-box adversarial attack for poisoning clustering [78.19784577498031]
  We propose a black-box adversarial attack for crafting adversarial samples to test the robustness of clustering algorithms. We show that our attacks are transferable even against supervised algorithms such as SVMs, random forests, and neural networks.
  arXiv  Detail & Related papers  (2020-09-09T18:19:31Z)
• Adversarial EXEmples: A Survey and Experimental Evaluation of Practical Attacks on Machine Learning for Windows Malware Detection [67.53296659361598]
  adversarial EXEmples can bypass machine learning-based detection by perturbing relatively few input bytes. We develop a unifying framework that does not only encompass and generalize previous attacks against machine-learning models, but also includes three novel attacks. These attacks, named Full DOS, Extend and Shift, inject the adversarial payload by respectively manipulating the DOS header, extending it, and shifting the content of the first section.
  arXiv  Detail & Related papers  (2020-08-17T07:16:57Z)
• Adversarial Machine Learning Attacks and Defense Methods in the Cyber Security Domain [58.30296637276011]
  This paper summarizes the latest research on adversarial attacks against security solutions based on machine learning techniques. It is the first to discuss the unique challenges of implementing end-to-end adversarial attacks in the cyber security domain.
  arXiv  Detail & Related papers  (2020-07-05T18:22:40Z)
• Adversarial vs behavioural-based defensive AI with joint, continual and active learning: automated evaluation of robustness to deception, poisoning and concept drift [62.997667081978825]
  Recent advancements in Artificial Intelligence (AI) have brought new capabilities to behavioural analysis (UEBA) for cyber-security. In this paper, we present a solution to effectively mitigate this attack by improving the detection process and efficiently leveraging human expertise.
  arXiv  Detail & Related papers  (2020-01-13T13:54:36Z)

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.