Search Results for author:
Found 13 papers, 3 papers with code
Fully Attentional Networks with Self-emerging Token Labeling
With the proposed STL framework, our best model based on FAN-L-Hybrid (77. 3M parameters) achieves 84. 8% Top-1 accuracy and 42. 1% mCE on ImageNet-1K and ImageNet-C, and sets a new state-of-the-art for ImageNet-A (46. 1%) and ImageNet-R (56. 6%) without using extra data, outperforming the original FAN counterpart by significant margins.
Ranked #16 on
Domain Generalization
on ImageNet-C
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify.
Machine Unlearning in Gradient Boosting Decision Trees
To the best of our knowledge, this is the first work that considers machine unlearning on GBDT.
Marksman Backdoor: Backdoor Attacks with Arbitrary Target Class
To achieve this goal, we propose to represent the trigger function as a class-conditional generative model and to inject the backdoor in a constrained optimization framework, where the trigger function learns to generate an optimal trigger pattern to attack any target class at will while simultaneously embedding this generative backdoor into the trained model.
NL2GDPR: Automatically Develop GDPR Compliant Android Application Features from Natural Language
At the core, NL2GDPR is a privacy-centric information extraction model, appended with a GDPR policy finder and a policy generator.
DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding
After embedding, each model will respond distinctively to these key samples, which creates a model-unique signature as a strong tool for authentication and user identity.
Defending Backdoor Attacks on Vision Transformer via Patch Processing
We first examine the vulnerability of ViTs against various backdoor attacks and find that ViTs are also quite vulnerable to existing attacks.
Backdoor Attack with Imperceptible Input and Latent Modification
Many existing countermeasures found that backdoor tends to leave tangible footprints in the latent or feature space, which can be utilized to mitigate backdoor attacks. In this paper, we extend the concept of imperceptible backdoor from the input space to the latent representation, which significantly improves the effectiveness against the existing defense mechanisms, especially those relying on the distinguishability between clean inputs and backdoor inputs in latent space.
Robust Watermarking for Deep Neural Networks via Bi-Level Optimization
Deep neural networks (DNNs) have become state-of-the-art in many application domains.
LIRA: Learnable, Imperceptible and Robust Backdoor Attacks
Under this optimization framework, the trigger generator function will learn to manipulate the input with imperceptible noise to preserve the model performance on the clean data and maximize the attack success rate on the poisoned data.
Towards Class-Oriented Poisoning Attacks Against Neural Networks
Poisoning attacks on machine learning systems compromise the model performance by deliberately injecting malicious samples in the training dataset to influence the training process.
Rallying Adversarial Techniques against Deep Learning for Network Security
Recent advances in artificial intelligence and the increasing need for powerful defensive measures in the domain of network security, have led to the adoption of deep learning approaches for use in network intrusion detection systems.
Hardware Trojan Attacks on Neural Networks
With the rising popularity of machine learning and the ever increasing demand for computational power, there is a growing need for hardware optimized implementations of neural networks and other machine learning models.
