Search Results for author:
Found 15 papers, 8 papers with code
A General Framework for Data-Use Auditing of ML Models
Auditing the use of data in training machine-learning (ML) models is an increasingly pressing challenge, as myriad ML practitioners routinely leverage the effort of content creators to train models without their permission.
Concealing Backdoor Model Updates in Federated Learning by Trigger-Optimized Data Poisoning
To effectively conceal malicious model updates among benign ones, we propose DPOT, a backdoor attack strategy in FL that dynamically constructs backdoor objectives by optimizing a backdoor trigger, making backdoor data have minimal effect on model updates.
Mudjacking: Patching Backdoor Vulnerabilities in Foundation Models
However, foundation models are vulnerable to backdoor attacks and a backdoored foundation model is a single-point-of-failure of the AI ecosystem, e. g., multiple downstream classifiers inherit the backdoor vulnerabilities simultaneously.
Mendata: A Framework to Purify Manipulated Training Data
Untrusted data used to train a model might have been manipulated to endow the learned model with hidden properties that the data contributor might later exploit.
Group-based Robustness: A General Framework for Customized Robustness in the Real World
In this work, we identify real-world scenarios where the true threat cannot be assessed accurately by existing attacks.
Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks
First, we demonstrate a loss function that explicitly encodes (1) and show that Auto-PGD finds more attacks with it.
Practical Integration via Separable Bijective Networks
Neural networks have enabled learning over examples that contain thousands of dimensions.
Defense Through Diverse Directions
In this work we develop a novel Bayesian neural network methodology to achieve strong adversarial robustness without the need for online adversarial training.
Malware Makeover: Breaking ML-based Static Analysis by Modifying Executable Bytes
Moreover, we found that our attack can fool some commercial anti-viruses, in certain cases with a success rate of 85%.
$n$-ML: Mitigating Adversarial Examples via Ensembles of Topologically Manipulated Classifiers
This paper proposes a new defense called $n$-ML against adversarial examples, i. e., inputs crafted by perturbing benign inputs by small amounts to induce misclassifications by classifiers.
SBFT: a Scalable and Decentralized Trust Infrastructure
SBFT is a state of the art Byzantine fault tolerant permissioned blockchain system that addresses the challenges of scalability, decentralization and world-scale geo-replication.
Distributed, Parallel, and Cluster Computing
HotStuff: BFT Consensus in the Lens of Blockchain
We present HotStuff, a leader-based Byzantine fault-tolerant replication protocol for the partially synchronous model.
Distributed, Parallel, and Cluster Computing
On the Suitability of $L_p$-norms for Creating and Preventing Adversarial Examples
Combined with prior work, we thus demonstrate that nearness of inputs as measured by $L_p$-norms is neither necessary nor sufficient for perceptual similarity, which has implications for both creating and defending against adversarial examples.
A General Framework for Adversarial Examples with Objectives
Images perturbed subtly to be misclassified by neural networks, called adversarial examples, have emerged as a technically deep challenge and an important concern for several application domains.
Stealing Machine Learning Models via Prediction APIs
In such attacks, an adversary with black-box access, but no prior knowledge of an ML model's parameters or training data, aims to duplicate the functionality of (i. e., "steal") the model.
