arXiv research

Saliency maps are often used in computer vision to provide intuitive interpretations of what input regions a model has used to produce a specific prediction. A number of approaches to saliency map generation are available, but most require access to model parameters. This work proposes an approach for saliency map gene…

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information."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 -…

Paper proposes a method to generate adversarial perturbations for black-box attacks without accessing inner states.

Paper proposes a new black-box attack approach to minimize visual distortion.

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 …

In this paper, we propose an improvement of Adversarial Transformation Networks(ATN) to generate adversarial examples, which can fool white-box models and black-box models with a state of the art performance and won the 2rd place in the non-target task in CAAD 2018.

Automatically jailbreaks LLMs with black-box access.

New method generates clean data from corrupted observations.

Paper proposes B3D method for black-box backdoor detection.

Understanding how a learned black box works is of crucial interest for the future of Machine Learning. In this paper, we pioneer the question of the global interpretability of learned black box models that assign numerical values to symbolic sequential data. To tackle that task, we propose a spectral algorithm for the …

Multi-party machine learning leaks global dataset properties even with black-box access.

New analysis improves black-box $k$-PCA algorithms, reducing parameter loss.

Paper presents efficient IS for tail risk estimation with machine learning features.

Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized re-distribution, watermarking approaches have been introduced in the past couple of years. W…

New black-box attack method improves GNN defense without needing training data.

The paper extends statistical inference methods for black-box generative models.

We study the problem of generating adversarial examples in a black-box setting in which only loss-oracle access to a model is available. We introduce a framework that conceptually unifies much of the existing work on black-box attacks, and we demonstrate that the current state-of-the-art methods are optimal in a natura…

Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be addressed, particularly the potential for unintentional discrimination. We present an…

New approach improves black-box planning efficiency by discovering focused macros.

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

Improves model classification accuracy in black-box settings.

Adapts example weights to optimize black-box metrics.

In this paper, we study the problem of constrained robust (min-max) optimization ina black-box setting, where the desired optimizer cannot access the gradients of the objective function but may query its values. We present a principled optimization framework, integrating a zeroth-order (ZO) gradient estimator with an a…

New method attacks GNNs with limited node access, increasing misclassification rate.

Paper proposes a black-box technique to generate adversarial samples.

IReEn reveals functionality of black-box agents via iterative neural synthesis.

RelEx explains relational models without gradient access.

Adversarial examples pose a threat to deep neural network models in a variety of scenarios, from settings where the adversary has complete knowledge of the model and to the opposite "black box" setting. Black box attacks are particularly threatening as the adversary only needs access to the input and output of the mode…

Improves relevancy of black-box anomaly detectors with user feedback.

Method differentiates diffusion model training to predict sample sensitivity.

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…

In this paper, we consider the problem of black box continuous submodular maximization where we only have access to the function values and no information about the derivatives is provided. For a monotone and continuous DR-submodular function, and subject to a bounded convex body constraint, we propose Black-box Contin…

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 …

Efficiently controls unknown linear systems with black-box interactions.

Develops transparent global models consistent with local explanations.

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

Attack reveals model details from counterfactual explanations.

With the great success of graph embedding model on both academic and industry area, the robustness of graph embedding against adversarial attack inevitably becomes a central problem in graph learning domain. Regardless of the fruitful progress, most of the current works perform the attack in a white-box fashion: they n…

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

Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction attacks, in which an adversary extracts an approximation of MLaaS models by making bla…

We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $\ell_\infty$ and $\ell_2$ metrics, where only loss-oracle access to the model is available. On two public black-box attack challenges, the algorithm achieves the highest evasion rate, sur…

VOGP efficiently identifies Pareto optimal solutions in black-box vector optimization.

Machine learning has seen tremendous advances in the past few years, which has lead to deep learning models being deployed in varied applications of day-to-day life. Attacks on such models using perturbations, particularly in real-life scenarios, pose a severe challenge to their applicability, pushing research into the…

Depending on how much information an adversary can access to, adversarial attacks can be classified as white-box attack and black-box attack. For white-box attack, optimization-based attack algorithms such as projected gradient descent (PGD) can achieve relatively high attack success rates within moderate iterates. How…

Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples resulting from adding small-magnitude perturbations to inputs. Such adversarial examples can mislead DNNs to produce adversary-selected results. Different attack strategies have been proposed to generate adversarial examples, but how t…

Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how different features influence the model prediction. This is important when interpreting…

Protocol assesses better model among two opaque models with minimal interaction.

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data, thereby identifying training points most responsible for a given prediction. To …