SEC
1.7K papers
Towards Evaluating the Robustness of Neural Networks
Neural networks provide state-of-the-art results for most machine learning tasks. Unfortunately, neural networks are vulnerable to adversarial examples: given an input $x$ and any target...
Deep Learning with Differential Privacy
Machine learning techniques based on neural networks are achieving remarkable results in a wide variety of domains. Often, the training of models requires large, representative datasets, which may...
Membership Inference Attacks against Machine Learning Models
We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a...
The Limitations of Deep Learning in Adversarial Settings
Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the...
Practical Black-Box Attacks against Machine Learning
Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to...
Extracting Training Data from Large Language Models
It has become common to publish large (billion parameter) language models that have been trained on private datasets. This paper demonstrates that in such settings, an adversary can perform a...
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
Deep learning algorithms have been shown to perform extremely well on many classical machine learning problems. However, recent studies have shown that deep learning, like other machine learning...
Spectre Attacks: Exploiting Speculative Execution
Modern processors use branch prediction and speculative execution to maximize performance. For example, if the destination of a branch depends on a memory value that is in the process of being...
Federated Learning with Differential Privacy: Algorithms and Performance Analysis
In this paper, to effectively prevent information leakage, we propose a novel framework based on the concept of differential privacy (DP), in which artificial noises are added to the parameters at...
The Queen's Guard: A Secure Enforcement of Fine-grained Access Control In Distributed Data Analytics Platforms
Distributed data analytics platforms (i.e., Apache Spark, Hadoop) provide high-level APIs to programmatically write analytics tasks that are run distributedly in multiple computing nodes. The...
Stealing Machine Learning Models via Prediction APIs
Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are...
Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
Although deep neural networks (DNNs) have achieved great success in many tasks, they can often be fooled by \emph{adversarial examples} that are generated by adding small but purposeful...
Jailbreaking Black Box Large Language Models in Twenty Queries
There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, which coax LLMs into...
Local Model Poisoning Attacks to Byzantine-Robust Federated Learning
In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master device maintains a...
Renyi Differential Privacy
We propose a natural relaxation of differential privacy based on the Renyi divergence. Closely related notions have appeared in several recent papers that analyzed composition of differentially...
Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
Deep Learning has recently become hugely popular in machine learning, providing significant improvements in classification accuracy in the presence of highly-structured and large databases....
Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
Deep neural networks are susceptible to various inference attacks as they remember information about their training data. We design white-box inference attacks to perform a comprehensive privacy...
ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Models
Deep neural networks (DNNs) are one of the most prominent technologies of our time, as they achieve state-of-the-art performance in many machine learning tasks, including but not limited to image...