Search Results for author:
Found 16 papers, 4 papers with code
DAD++: Improved Data-free Test Time Adversarial Defense
With the increasing deployment of deep neural networks in safety-critical applications such as self-driving cars, medical imaging, anomaly detection, etc., adversarial robustness has become a crucial concern in the reliability of these networks in real-world scenarios.
DISBELIEVE: Distance Between Client Models is Very Essential for Effective Local Model Poisoning Attacks
Leveraging this, we introduce DISBELIEVE, a local model poisoning attack that creates malicious parameters or gradients such that their distance to benign clients' parameters or gradients is low respectively but at the same time their adverse effect on the global model's performance is high.
Adaptive Self-Distillation for Minimizing Client Drift in Heterogeneous Federated Learning
In practice, there can often be substantial heterogeneity (e. g., class imbalance) across the local data distributions observed by each of these clients.
Query Efficient Cross-Dataset Transferable Black-Box Attack on Action Recognition
By using a nearly disjoint dataset to train the substitute model, our method removes the requirement that the substitute model be trained using the same dataset as the target model, and leverages queries to the target model to retain the fooling rate benefits provided by query-based methods.
Robust Few-shot Learning Without Using any Adversarial Samples
These methods rely on the generation of adversarial samples in every episode of training, which further adds a computational burden.
Data-free Defense of Black Box Models Against Adversarial Attacks
At test time, WNR combined with trained regenerator network is prepended to the black box network, resulting in a high boost in adversarial accuracy.
DE-CROP: Data-efficient Certified Robustness for Pretrained Classifiers
Existing works use this technique to provably secure a pretrained non-robust model by training a custom denoiser network on entire training data.
Holistic Approach to Measure Sample-level Adversarial Vulnerability and its Utility in Building Trustworthy Systems
We, therefore, propose a holistic approach for quantifying adversarial vulnerability of a sample by combining these different perspectives, i. e., degree of model's reliance on high-frequency features and the (conventional) sample-distance to the decision boundary.
DAD: Data-free Adversarial Defense at Test Time
Deep models are highly susceptible to adversarial attacks.
Beyond Classification: Knowledge Distillation using Multi-Object Impressions
Knowledge Distillation (KD) utilizes training data as a transfer set to transfer knowledge from a complex network (Teacher) to a smaller network (Student).
Incremental Learning for Animal Pose Estimation using RBF k-DPP
Thus, in this work, we propose a novel problem of "Incremental Learning for Animal Pose Estimation".
Mining Data Impressions from Deep Models as Substitute for the Unavailable Training Data
We dub them "Data Impressions", which act as proxy to the training data and can be used to realize a variety of tasks.
Effectiveness of Arbitrary Transfer Sets for Data-free Knowledge Distillation
In such scenarios, existing approaches either iteratively compose a synthetic set representative of the original training dataset, one sample at a time or learn a generative model to compose such a transfer set.
Fusion of Deep and Non-Deep Methods for Fast Super-Resolution of Satellite Images
In the emerging commercial space industry there is a drastic increase in access to low cost satellite imagery.
DeGAN : Data-Enriching GAN for Retrieving Representative Samples from a Trained Classifier
We use the available data, that may be an imbalanced subset of the original training dataset, or a related domain dataset, to retrieve representative samples from a trained classifier, using a novel Data-enriching GAN (DeGAN) framework.
Zero-Shot Knowledge Distillation in Deep Networks
Without even using any meta-data, we synthesize the Data Impressions from the complex Teacher model and utilize these as surrogates for the original training data samples to transfer its learning to Student via knowledge distillation.
