Search Results for author:
Found 21 papers, 11 papers with code
SoK: Analyzing Adversarial Examples: A Framework to Study Adversary Knowledge
We focus on the image classification domain and provide a theoretical framework to study adversary knowledge inspired by work in order theory.
Universal Backdoor Attacks
We demonstrate the effectiveness and robustness of our universal backdoor attacks by controlling models with up to 6, 000 classes while poisoning only 0. 15% of the training dataset.
Leveraging Optimization for Adaptive Attacks on Image Watermarks
A core security property of watermarking is robustness, which states that an attacker can only evade detection by substantially degrading image quality.
Identifying and Mitigating the Security Risks of Generative AI
However, GenAI can be used just as well by attackers to generate new attacks and increase the velocity and efficacy of existing attacks.
Backdooring Textual Inversion for Concept Censorship
Users can easily download the word embedding from public websites like Civitai and add it to their own stable diffusion model without fine-tuning for personalization.
Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions
Motivated by the success of previous work co-designing machine learning and MPC, we develop an activation function co-design.
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks
Our research points to intrinsic flaws in current attack evaluation methods and raises the bar for all data poisoning attackers who must delicately balance this trade-off to remain robust and undetectable.
PTW: Pivotal Tuning Watermarking for Pre-Trained Image Generators
We propose an adaptive attack that can successfully remove any watermarking with access to only 200 non-watermarked images.
Towards Robust Dataset Learning
In this paper, we study the problem of learning a robust dataset such that any classifier naturally trained on the dataset is adversarially robust.
The Limits of Word Level Differential Privacy
As the issues of privacy and trust are receiving increasing attention within the research community, various attempts have been made to anonymize textual data.
Assessing Differentially Private Variational Autoencoders under Membership Inference
We present an approach to quantify and compare the privacy-accuracy trade-off for differentially private Variational Autoencoders.
Feature Grinding: Efficient Backdoor Sanitation in Deep Neural Networks
Feature Grinding requires at most six percent of the model's training time on CIFAR-10 and at most two percent on ImageNet for sanitizing the surveyed backdoors.
SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)
Watermarking should be robust against watermark removal attacks that derive a surrogate model that evades provenance verification.
Quantifying identifiability to choose and audit $ε$ in differentially private deep learning
We transform $(\epsilon,\delta)$ to a bound on the Bayesian posterior belief of the adversary assumed by differential privacy concerning the presence of any record in the training dataset.
Investigating Membership Inference Attacks under Data Dependencies
Our results reveal that training set dependencies can severely increase the performance of MIAs, and therefore assuming that data samples are statistically independent can significantly underestimate the performance of MIAs.
Assessing differentially private deep learning with Membership Inference
We empirically compare local and central differential privacy mechanisms under white- and black-box membership inference to evaluate their relative privacy-accuracy trade-offs.
Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
We propose a fingerprinting method for deep neural network classifiers that extracts a set of inputs from the source model so that only surrogates agree with the source model on the classification of such inputs.
RIGA: Covert and Robust White-Box Watermarking of Deep Neural Networks
White-box watermarking algorithms have the advantage that they do not impact the accuracy of the watermarked model.
On the Robustness of the Backdoor-based Watermarking in Deep Neural Networks
We focus on backdoor-based watermarking and propose two -- a black-box and a white-box -- attacks that remove the watermark.
SynTF: Synthetic and Differentially Private Term Frequency Vectors for Privacy-Preserving Text Mining
Text mining and information retrieval techniques have been developed to assist us with analyzing, organizing and retrieving documents with the help of computers.
HardIDX: Practical and Secure Index with SGX
Software-based approaches for search over encrypted data are still either challenged by lack of proper, low-leakage encryption or slow performance.
Cryptography and Security
