arXiv research

Game theory helps machine learn better from adversarial queries.

We use Bayesian optimization to create efficient adversarial attacks with limited queries.

NP-Attack reduces query counts for black-box adversarial attacks.

Study on how many queries an adversary needs to make to match the best attack in white-box model.

Lower bounds on queries for Bayesian private learning.

Sign-OPT uses fewer queries to generate adversarial examples.

Efficient method for generating adversarial examples with limited query budget.

New methods improve black-box adversarial attacks with fewer queries.

AdvMind detects adversary intent in black-box attacks with high accuracy.

Deep neural networks have recently achieved tremendous success in image classification. Recent studies have however shown that they are easily misled into incorrect classification decisions by adversarial examples. Adversaries can even craft attacks by querying the model in black-box settings, where no information abou…

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods -…

BOBYQA optimizes deep networks with fewer queries than other methods.

AdversarialPSO uses fewer queries to create high-success-rate adversarial examples.

LSDAT reduces query efficiency for decision-based adversarial attacks.

Machine learning models are vulnerable to adversarial examples. An adversary modifies the input data such that humans still assign the same label, however, machine learning models misclassify it. Previous approaches in the literature demonstrated that adversarial examples can even be generated for the remotely hosted m…

New method for black-box adversarial attacks using pretrained model embeddings.

We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a transfer gradient of a surrogate white-box model, or based on the query feedback. Ho…

Paper proposes ZO-NGD for more efficient black-box attacks.

We investigate how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks in a black-box setting. We formalize the problem setting and systematically evaluate what benefits the adversary can gain by using substitute models. We show that there is an exploration-exploita…

P-BO reduces black-box adversarial attacks by 10x with Bayesian optimization and function prior.

Develops robust few-shot learning models resistant to adversarial attacks.

We formulate a private learning model to study an intrinsic tradeoff between privacy and query complexity in sequential learning. Our model involves a learner who aims to determine a scalar value, $v^*$, by sequentially querying an external database and receiving binary responses. In the meantime, an adversary observes…

New framework for efficient query-based imitation learning.

This work addresses dynamic KDE data structures with robustness to adversarial queries.

We propose a new active learning by query synthesis approach using Generative Adversarial Networks (GAN). Different from regular active learning, the resulting algorithm adaptively synthesizes training instances for querying to increase learning speed. We generate queries according to the uncertainty principle, but our…

Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query access to the network and solving for a successful adversarial example becomes much …

Bayesian optimisation method targets graph classification models against adversarial attacks.

New algorithm finds corrupted vertices in graphs with few queries.

Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more restrictive than the typical black-box model where the adversary can observe the full …

Study optimizes query strategy for private learning in eavesdropping scenarios.

Study exact partition recovery with same-cluster oracle, bounded error.

Spanning attack improves black-box attacks with unlabeled data.

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human eyes but will be misclassified by a well-trained classifier. In this paper, we fo…

Study adversarial perturbations in classification, analyzing learning and certification.

Recent studies have highlighted that deep neural networks (DNNs) are vulnerable to adversarial attacks, even in a black-box scenario. However, most of the existing black-box attack algorithms need to make a huge amount of queries to perform attacks, which is not practical in the real world. We note one of the main reas…

Algorithm adapts to shifting domains with minimal label queries.

Recent studies have shown that adversarial examples in state-of-the-art image classifiers trained by deep neural networks (DNN) can be easily generated when the target model is transparent to an attacker, known as the white-box setting. However, when attacking a deployed machine learning service, one can only acquire t…

Deep neural networks (DNNs) are known for their vulnerability to adversarial examples. These are examples that have undergone small, carefully crafted perturbations, and which can easily fool a DNN into making misclassifications at test time. Thus far, the field of adversarial research has mainly focused on image model…

Proposes a query-efficient blackbox attack method.

Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary by omitting probability scores, significantly impacting the utility of the provid…

Lower bounds on query complexity for reconstructing private learner's training data.

New algorithm tackles dynamic query routing to multiple embedding models.

The paper addresses learner privacy in convex optimization with feedback.

Optimizes query routing to LLMs under cost and resource constraints.

We study black-box attacks on machine learning classifiers where each query to the model incurs some cost or risk of detection to the adversary. We focus explicitly on minimizing the number of queries as a major objective. Specifically, we consider the problem of attacking machine learning classifiers subject to a budg…

We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversarial images has the additional constraint on query budget, and efficient attacks remain an open problem to date. With only the mild assumpti…

DAmageNet generates universal adversarial samples with high transferability.

Adversarial MoE learns category-specific models for product search.