Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

3.2%6.3%9.5%12.6% · Oct 202519922001200920172026
48 results for Adaptive Defense

Automated discovery of adaptive attacks improves adversarial defense evaluation.

problem Challenges in reliably evaluating adversarial defenses.
method Formalizes adaptive attacks as reusable building blocks in a search space for automatic discovery.
result Our tool discovers significantly stronger attacks than AutoAttack, improving adversarial defense evaluation.

New defense method inspired by encryption improves visual classification accuracy.

problem Conventional defenses reduce accuracy and are defeated by obfuscated gradients.
method Block-wise pixel shuffling with secret key for training and test images.
result Achieves high accuracy (91.55%) on clean images and (89.66%) on adversarial examples.

New research shows many recent defenses against adversarial examples are ineffective against black-box attacks.

problem The robustness of recent defenses against adversarial examples is insufficient, especially against black-box attacks.
method Evaluation of nine defenses on two black-box adversarial models and six attacks on CIFAR-10 and Fashion-MNIST datasets.
result Most recent defenses provide only marginal improvements in security (<25%<25\%) compared to undefended networks.

Correctly evaluating defenses against adversarial examples has proven to be extremely difficult. Despite the significant amount of recent work attempting to design defenses that withstand adaptive attacks, few have succeeded; most papers that propose defenses are quickly shown to be incorrect. We believe a large contri…

2019-02-18abs ↗pdf ↗

ADAPT improves robustness of Vision Transformers without full model fine-tuning.

problem Vulnerability of Vision Transformers to adversarial attacks.
method Parameter-efficient prompt tuning with ADAPT framework for adaptive adversarial training.
result ADAPT achieves robust accuracy of ~40% w.r.t. SOTA methods using only ~1% of the parameters.

New research evaluates various perturbation methods for improving neural network robustness.

problem Understanding and improving robustness of Convolutional Neural Networks (CNNs) against adversarial attacks.
method Detailed evaluation of five main perturbation-based defenses, comparing random and deterministic approaches.
result Perturbation-based defenses are equivalent in efficacy, and attacks transfer between them.

DAD++ improves test-time adversarial defense without access to training data.

problem Improving adversarial robustness of pre-trained models without access to training data.
method Test-time Data-free Adversarial Defense (DAD++) with detection and correction schemes.
result DAD++ significantly improves adversarial robustness with minimal clean accuracy drop.

Proposes RPG-RT for red-teaming T2I models without internal access.

problem Evaluating T2I models' security through red-teaming is challenging due to their closed-source nature and unknown defense mechanisms.
method Integrates LLM and rule-based preference modeling to dynamically adapt to unknown defense mechanisms.
result Demonstrates superior and practical approach for red-teaming T2I models.

Paper proposes HRS to improve neural network robustness without significant accuracy loss.

problem Vulnerability of neural networks to adversarial attacks and performance degradation.
method Hierarchical Random Switching (HRS) for robustness without sacrificing accuracy.
result HRS significantly improves adversarial robustness with minimal accuracy loss.

Adaptive Misinformation defends against model stealing attacks by sending incorrect predictions for OOD queries.

problem Model stealing attacks clone target models using black-box query access and a surrogate dataset.
method Selective sending of incorrect predictions for Out-Of-Distribution (OOD) queries to degrade attacker's clone model accuracy.
result Our defense reduces attacker's clone model accuracy by up to 40% while maintaining benign user accuracy under 0.5%.

This work develops agents to learn generalizable policies for dynamic network environments.

problem Real-world network topologies change due to attackers, defenders, or system failures, leading to failures in adaptive ACD systems.
method Developing agents to learn generalizable policies across dynamic network environments.
result Agents can learn robust policies for dynamic network topologies and diverse attackers.

In this appraisal paper, we evaluate the efficacy of SHIELD, a compression-based defense framework for countering adversarial attacks on image classification models, which was published at KDD 2018. Here, we consider alternative threat models not studied in the original work, where we assume that an adaptive adversary …

2019-02-01abs ↗pdf ↗

This paper improves model robustness against adversarial attacks using optimal transport.

problem Adversarial attacks can mislead deep learning models with imperceptible perturbations.
method Exploits optimal transport theory to align adversarial and original image distributions.
result SAT (Sinkhorn Adversarial Training) leads to more robust models compared to state-of-the-art.

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning algorithm. Although a significant body of work on developing defensive models has …

2018-09-10abs ↗pdf ↗

ATHENA builds flexible defenses against adversarial attacks.

problem Extensive research on adversarial attacks is domain-specific and cannot be easily extended.
method Designing an extensible framework based on diverse weak defenses.
result Comprehensive empirical study demonstrates the effectiveness of ATHENA.

Graph neural networks are vulnerable to adversarial attacks by manipulating graph structure.

problem Vulnerability of Graph Neural Networks to adversarial attacks.
method Categorization and review of existing attacks and defenses.
result Developed a repository for empirical studies on graph adversarial attacks and defenses.

Paper analyzes adversarial attacks and defenses using game theory.

problem Unclear conditions for optimal attacks and defenses in adversarial learning.
method Game-theoretic framework with locally linear decision boundary model.
result Fast Gradient Method attack and Randomized Smoothing defense form a Nash Equilibrium.

Topology-aware generative models improve manifold-based defenses against adversarial examples.

problem Adversarial examples compromise the reliability of ML models, especially DNNs.
method Investigate if generative models used in manifold-based defenses need to be topology-aware.
result Topology-aware generative models enhance the robustness of manifold-based defenses.

New defense against DNN model stealing attacks by poisoning predictions.

problem Stealing DNN models through black-box access attacks.
method Active perturbation of predictions to mislead attacker's training.
result Effective against a wide range of DNN stealing attacks, reducing attacker's success rate significantly.

An adversarial machine learning approach is introduced to launch jamming attacks on wireless communications and a defense strategy is presented. A cognitive transmitter uses a pre-trained classifier to predict the current channel status based on recent sensing results and decides whether to transmit or not, whereas a j…

2018-07-03abs ↗pdf ↗

This study evaluates adversarial attacks and defenses for chest X-ray disease classification.

problem Vulnerability of deep neural networks to adversarial examples in chest X-ray disease detection.
method Detailed introduction and evaluation of various attack and defense methods.
result Attack and defense methods perform poorly with excessive iterations and large perturbations.

Stochastic defense improves natural classifiers against adversarial attacks.

problem Vulnerability of deep networks to adversarial attacks.
method Long-run MCMC sampling with Energy-Based Model for adversarial purification.
result Balancing memoryless and metastable behavior leads to effective purification and robust classification.

Data poisoning attacks -- where an adversary can modify a small fraction of training data, with the goal of forcing the trained classifier to high loss -- are an important threat for machine learning in many applications. While a body of prior work has developed attacks and defenses, there is not much general understan…

2019-05-28abs ↗pdf ↗

BlurNet defends against adversarial attacks by filtering feature maps.

problem Adversarial attacks on deep neural networks, especially for image classification.
method BlurNet introduces a depthwise convolution layer with standard blur kernels after the first layer to filter high frequency noise.
result The defense reduces the success rate of adversarial attacks from 90% to 20% with total variation regularization.

Adversarial examples that fool machine learning models, particularly deep neural networks, have been a topic of intense research interest, with attacks and defenses being developed in a tight back-and-forth. Most past defenses are best effort and have been shown to be vulnerable to sophisticated attacks. Recently a set…

2018-02-09abs ↗pdf ↗

BUZz defends images from adversarial attacks using simple transformations.

problem Adversarial attacks on deep neural networks for image classification.
method Combination of deep neural networks and simple image transformations.
result Achieves significant improvement over state-of-the-art defenses with a modest drop in clean accuracy.

Deep Partition Aggregation defends against poisoning attacks with provable certificates.

problem Adversarial poisoning attacks corrupt classifier test-time behavior.
method Deep Partition Aggregation (DPA) is an ensemble method using hash partitions and base models trained on these partitions.
result DPA can certify >= 50% of test images against over 500 poison image insertions on MNIST, and nine insertions on CIFAR-10.

DNCF framework recovers real scenes from imperfect images robustly.

problem Recovering real scenes from imperfect images.
method Nonparametric deep network that learns physical image formation equations.
result DNCF framework robustly defends against adversarial attacks.

Unified framework for analyzing model stealing attacks and defenses.

problem Vulnerability of ML applications to model stealing attacks.
method Developed a rigorous threat model and evaluation criteria, proposed methods to quantify attack and defense strategies.
result Demonstrated the importance of attack-specific perturbations for effective defenses.