Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits

• URL: http://arxiv.org/abs/2402.13487v1
• Date: Wed, 21 Feb 2024 02:54:00 GMT
• Title: Stealthy Adversarial Attacks on Stochastic Multi-Armed Bandits
• Authors: Zhiwei Wang, Huazheng Wang, Hongning Wang
• Abstract summary: Adversarial attacks against multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and find most existing attacks can be easily detected by our proposed detection method. This motivates us to study the notion of stealthy attack against MABs and investigate the resulting attackability.
• Score: 46.6541562214783
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Adversarial attacks against stochastic multi-armed bandit (MAB) algorithms have been extensively studied in the literature. In this work, we focus on reward poisoning attacks and find most existing attacks can be easily detected by our proposed detection method based on the test of homogeneity, due to their aggressive nature in reward manipulations. This motivates us to study the notion of stealthy attack against stochastic MABs and investigate the resulting attackability. Our analysis shows that against two popularly employed MAB algorithms, UCB1 and $\epsilon$-greedy, the success of a stealthy attack depends on the environmental conditions and the realized reward of the arm pulled in the first round. We also analyze the situation for general MAB algorithms equipped with our attack detection method and find that it is possible to have a stealthy attack that almost always succeeds. This brings new insights into the security risks of MAB algorithms.

Related papers

• AdvQDet: Detecting Query-Based Adversarial Attacks with Adversarial Contrastive Prompt Tuning [93.77763753231338]
  Adversarial Contrastive Prompt Tuning (ACPT) is proposed to fine-tune the CLIP image encoder to extract similar embeddings for any two intermediate adversarial queries. We show that ACPT can detect 7 state-of-the-art query-based attacks with $>99%$ detection rate within 5 shots. We also show that ACPT is robust to 3 types of adaptive attacks.
  arXiv  Detail & Related papers  (2024-08-04T09:53:50Z)
• Meta Invariance Defense Towards Generalizable Robustness to Unknown Adversarial Attacks [62.036798488144306]
  Current defense mainly focuses on the known attacks, but the adversarial robustness to the unknown attacks is seriously overlooked. We propose an attack-agnostic defense method named Meta Invariance Defense (MID) We show that MID simultaneously achieves robustness to the imperceptible adversarial perturbations in high-level image classification and attack-suppression in low-level robust image regeneration.
  arXiv  Detail & Related papers  (2024-04-04T10:10:38Z)
• Adversarial Attacks on Adversarial Bandits [10.891819703383408]
  We show that the attacker is able to mislead any no-regret adversarial bandit algorithm into selecting a suboptimal target arm. This result implies critical security concern in real-world bandit-based systems.
  arXiv  Detail & Related papers  (2023-01-30T00:51:39Z)
• Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack [53.032801921915436]
  Human Activity Recognition (HAR) has been employed in a wide range of applications, e.g. self-driving cars. Recently, the robustness of skeleton-based HAR methods have been questioned due to their vulnerability to adversarial attacks. We show such threats exist, even when the attacker only has access to the input/output of the model. We propose the very first black-box adversarial attack approach in skeleton-based HAR called BASAR.
  arXiv  Detail & Related papers  (2022-11-21T09:51:28Z)
• Adversarial Attacks on Gaussian Process Bandits [47.84198626686564]
  We propose various adversarial attack methods with differing assumptions on the attacker's strength and prior information. Our goal is to understand adversarial attacks on GP bandits from both a theoretical and practical perspective. We demonstrate that adversarial attacks on GP bandits can succeed in forcing the algorithm towards $mathcalR_rm target$ even with a low attack budget.
  arXiv  Detail & Related papers  (2021-10-16T02:39:10Z)
• Robust Stochastic Linear Contextual Bandits Under Adversarial Attacks [81.13338949407205]
  Recent works show that optimal bandit algorithms are vulnerable to adversarial attacks and can fail completely in the presence of attacks. Existing robust bandit algorithms only work for the non-contextual setting under the attack of rewards. We provide the first robust bandit algorithm for linear contextual bandit setting under a fully adaptive and omniscient attack.
  arXiv  Detail & Related papers  (2021-06-05T22:20:34Z)
• Action-Manipulation Attacks Against Stochastic Bandits: Attacks and Defense [45.408568528354216]
  We introduce a new class of attack named action-manipulation attack. In this attack, an adversary can change the action signal selected by the user. To defend against this class of attacks, we introduce a novel algorithm that is robust to action-manipulation attacks.
  arXiv  Detail & Related papers  (2020-02-19T04:09:15Z)
• Robust Stochastic Bandit Algorithms under Probabilistic Unbounded Adversarial Attack [41.060507338755784]
  This paper investigates the attack model where an adversary attacks with a certain probability at each round, and its attack value can be arbitrary and unbounded if it attacks. We propose a novel sample median-based and exploration-aided UCB algorithm (called med-E-UCB) and a median-based $epsilon$-greedy algorithm (called med-$epsilon$-greedy) Both algorithms are provably robust to the aforementioned attack model. More specifically we show that both algorithms achieve $mathcalO(log T)$ pseudo-regret (i.e
  arXiv  Detail & Related papers  (2020-02-17T19:21:08Z)

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.