Data valuation, a critical aspect of data-centric ML research, aims to
q...
We present a novel defense, against backdoor attacks on Deep Neural Netw...
Food classification is an important task in health care. In this work, w...
Recently, there has been a surge of interest in introducing vision into ...
In privacy-preserving machine learning, differentially private stochasti...
An important question in deploying large language models (LLMs) is how t...
Finding classifiers robust to adversarial examples is critical for their...
The proliferation of global censorship has led to the development of a
p...
In this paper, we ask whether Vision Transformers (ViTs) can serve as an...
Representation learning, i.e. the generation of representations useful f...
Due to their decentralized nature, federated learning (FL) systems have ...
Analysis techniques are critical for gaining insight into network traffi...
The United Nations Consumer Protection Guidelines lists "access ... to
a...
Membership inference attacks are a key measure to evaluate privacy leaka...
Deep neural networks are known to be vulnerable to adversarially perturb...
The adversarial patch attack against image classification models aims to...
We present F-PKI, an enhancement to the HTTPS public-key infrastructure ...
An adversarial patch can arbitrarily manipulate image pixels within a
re...
We focus on the use of proxy distributions, i.e., approximations of the
...
Understanding the fundamental limits of robust supervised learning has
e...
We ask the following question: what training information is required to
...
State-of-the-art object detectors are vulnerable to localized patch hidi...
Log-based cyber threat hunting has emerged as an important solution to
c...
Log-based cyber threat hunting has emerged as an important solution to
c...
Evaluation of adversarial robustness is often error-prone leading to
ove...
Conventional detection and classification ("fingerprinting") problems
in...
Tor is the most well-known tool for circumventing censorship. Unfortunat...
Open-world machine learning (ML) combines closed-world models trained on...
With increasing expressive power, deep neural networks have significantl...
Recent advances in programmable switch hardware offer a fresh opportunit...
Localized adversarial patches aim to induce misclassification in machine...
Attacks on Internet routing are typically viewed through the lens of
ava...
Differential privacy (DP) has arisen as the state-of-the-art metric for
...
This paper aims to enable training and inference of neural networks in a...
Machine learning models are prone to memorizing sensitive data, making t...
Right to be forgotten, also known as the right to erasure, is the right ...
In safety-critical but computationally resource-constrained applications...
A set of about 80 researchers, practitioners, and federal agency program...
Federated learning (FL) is a machine learning setting where many clients...
While progress has been made in understanding the robustness of machine
...
Deep neural networks have achieved impressive performance in many
applic...
The arms race between attacks and defenses for machine learning models h...
A large body of recent work has investigated the phenomenon of evasion
a...
The need for countering Advanced Persistent Threat (APT) attacks has led...
Federated learning distributes model training among a multitude of agent...
Website fingerprinting attacks, which use statistical analysis on networ...
Advanced Persistent Threat (APT) attacks are sophisticated and stealthy,...
We determine information theoretic conditions under which it is possible...
Recently, advanced cyber attacks, which consist of a sequence of steps t...
The need for countering Advanced Persistent Threat (APT) attacks has led...