# Hybrid Batch Attacks: Finding Black-box Adversarial Examples with Limited Queries

arXiv: https://arxiv.org/abs/1908.07000 · HTML: https://mlsanity.com/paper/1908.07000/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Aug 2019.

## Built on by (most cited first, 30 of 33)

- ["Real Attackers Don't Compute Gradients": Bridging the Gap Between Adversarial ML Research and Practice](https://mlsanity.com/paper/2212.14315/) (2022)
- [Local Bayesian optimization via maximizing probability of descent](https://mlsanity.com/paper/2210.11662/) (2022)
- [Adversarial Illusions in Multi-Modal Embeddings](https://mlsanity.com/paper/2308.11804/) (2023)
- [Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective](https://mlsanity.com/paper/2302.09457/) (2023)
- [Ensemble-based Blackbox Attacks on Dense Prediction](https://mlsanity.com/paper/2303.14304/) (2023)
- [Query Efficient Decision Based Sparse Attacks Against Black-Box Deep Learning Models](https://mlsanity.com/paper/2202.00091/) (2022)
- [Blackbox Attacks via Surrogate Ensemble Search](https://mlsanity.com/paper/2208.03610/) (2022)
- [Smart App Attack: Hacking Deep Learning Models in Android Apps](https://mlsanity.com/paper/2204.11075/) (2022)
- [RamBoAttack: A Robust Query Efficient Deep Neural Network Decision Exploit](https://mlsanity.com/paper/2112.05282/) (2021)
- [Efficient Black-box Adversarial Attacks via Bayesian Optimization Guided by a Function Prior](https://mlsanity.com/paper/2405.19098/) (2024)
- [Efficient Query-Based Attack against ML-Based Android Malware Detection under Zero Knowledge Setting](https://mlsanity.com/paper/2309.01866/) (2023)
- [ADI: Adversarial Dominating Inputs in Vertical Federated Learning Systems](https://mlsanity.com/paper/2201.02775/) (2022)
- [Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation](https://mlsanity.com/paper/2106.06056/) (2021)
- [Local Black-box Adversarial Attacks: A Query Efficient Approach](https://mlsanity.com/paper/2101.01032/) (2021)
- [Decompiling x86 Deep Neural Network Executables](https://mlsanity.com/paper/2210.01075/) (2022)
- [Boosting the Transferability of Adversarial Examples via Local Mixup and Adaptive Step Size](https://mlsanity.com/paper/2401.13205/) (2024)
- [SoK: Pitfalls in Evaluating Black-Box Attacks](https://mlsanity.com/paper/2310.17534/) (2023)
- [ALIF: Low-Cost Adversarial Audio Attacks on Black-Box Speech Platforms using Linguistic Features](https://mlsanity.com/paper/2408.01808/) (2024)
- [Enhance transferability of adversarial examples with model architecture](https://mlsanity.com/paper/2202.13625/) (2022)
- [Unraveling the Key of Machine Learning-based Android Malware Detection](https://mlsanity.com/paper/2402.02953/) (2024)
- [Publishing Efficient On-device Models Increases Adversarial Vulnerability](https://mlsanity.com/paper/2212.13700/) (2022)
- [A First Physical-World Trajectory Prediction Attack via LiDAR-induced Deceptions in Autonomous Driving](https://mlsanity.com/paper/2406.11707/) (2024)
- [Towards Scalable and Robust Model Versioning](https://mlsanity.com/paper/2401.09574/) (2024)
- [STBA: Towards Evaluating the Robustness of DNNs for Query-Limited Black-box Scenario](https://mlsanity.com/paper/2404.00362/) (2024)
- [DASH: A Meta-Attack Framework for Synthesizing Effective and Stealthy Adversarial Examples](https://mlsanity.com/paper/2508.13309/) (2025)
- [Fight Fire with Fire: Combating Adversarial Patch Attacks using Pattern-randomized Defensive Patches](https://mlsanity.com/paper/2311.06122/) (2023)
- [ChainMarks: Securing DNN Watermark with Cryptographic Chain](https://mlsanity.com/paper/2505.04977/) (2025)
- [Accelerating Targeted Hard-Label Adversarial Attacks in Low-Query Black-Box Settings](https://mlsanity.com/paper/2505.16313/) (2025)
- [Towards Interpretable Adversarial Examples via Sparse Adversarial Attack](https://mlsanity.com/paper/2506.17250/) (2025)
- [SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Images](https://mlsanity.com/paper/2407.11073/) (2024)

## Abstract (arXiv)

We study adversarial examples in a black-box setting where the adversary only has API access to the target model and each query is expensive. Prior work on black-box adversarial examples follows one of two main strategies: (1) transfer attacks use white-box attacks on local models to find candidate adversarial examples that transfer to the target model, and (2) optimization-based attacks use queries to the target model and apply optimization techniques to search for adversarial examples. We propose hybrid attacks that combine both strategies, using candidate adversarial examples from local models as starting points for optimization-based attacks and using labels learned in optimization-based attacks to tune local models for finding transfer candidates. We empirically demonstrate on the MNIST, CIFAR10, and ImageNet datasets that our hybrid attack strategy reduces cost and improves success rates. We also introduce a seed prioritization strategy which enables attackers to focus their resources on the most promising seeds. Combining hybrid attacks with our seed prioritization strategy enables batch attacks that can reliably find adversarial examples with only a handful of queries.