Search Results for author:
Found 13 papers, 5 papers with code
Those Aren't Your Memories, They're Somebody Else's: Seeding Misinformation in Chat Bot Memories
We generate 150 examples of misinformation, of which 114 (76%) were remembered by BlenderBot 2 when combined with a personal statement.
DDoD: Dual Denial of Decision Attacks on Human-AI Teams
Artificial Intelligence (AI) systems have been increasingly used to make decision-making processes faster, more accurate, and more efficient.
Unintended Memorization and Timing Attacks in Named Entity Recognition Models
In this paper, we study the setting when NER models are available as a black-box service for identifying sensitive information in user documents and show that these models are vulnerable to membership inference on their training datasets.
MANDERA: Malicious Node Detection in Federated Learning via Ranking
Although we know that the benign gradients and Byzantine attacked gradients are distributed differently, to detect the malicious gradients is challenging due to (1) the gradient is high-dimensional and each dimension has its unique distribution and (2) the benign gradients and the attacked gradients are always mixed (two-sample test methods cannot apply directly).
Hidden Backdoors in Human-Centric Language Models
We are able to demonstrate the adversary's high success rate of attacks, while maintaining functionality for regular users, with triggers inconspicuous by the human administrators.
On the (In)Feasibility of Attribute Inference Attacks on Machine Learning Models
In this paper, we take a closer look at another inference attack reported in literature, called attribute inference, whereby an attacker tries to infer missing attributes of a partially known record used in the training dataset by accessing the machine learning model as an API.
Oriole: Thwarting Privacy against Trustworthy Deep Learning Models
Deep Neural Networks have achieved unprecedented success in the field of face recognition such that any individual can crawl the data of others from the Internet without their explicit permission for the purpose of training high-precision face recognition models, creating a serious violation of privacy.
Not one but many Tradeoffs: Privacy Vs. Utility in Differentially Private Machine Learning
In this work, we empirically evaluate various implementations of differential privacy (DP), and measure their ability to fend off real-world privacy attacks, in addition to measuring their core goal of providing accurate classifications.
Cryptography and Security
Deep Learning Backdoors
The trigger can take a plethora of forms, including a special object present in the image (e. g., a yellow pad), a shape filled with custom textures (e. g., logos with particular colors) or even image-wide stylizations with special filters (e. g., images altered by Nashville or Gotham filters).
With Great Dispersion Comes Greater Resilience: Efficient Poisoning Attacks and Defenses for Linear Regression Models
To this end, we analyze and develop a new poisoning attack algorithm.
On the Resilience of Biometric Authentication Systems against Random Inputs
The average false positive rate (FPR) of the system, i. e., the rate at which an impostor is incorrectly accepted as the legitimate user, may be interpreted as a measure of the success probability of such an attack.
Invisible Backdoor Attacks on Deep Neural Networks via Steganography and Regularization
We show that the proposed invisible backdoors can be fairly effective across various DNN models as well as four datasets MNIST, CIFAR-10, CIFAR-100, and GTSRB, by measuring their attack success rates for the adversary, functionality for the normal users, and invisibility scores for the administrators.
On Inferring Training Data Attributes in Machine Learning Models
A number of recent works have demonstrated that API access to machine learning models leaks information about the dataset records used to train the models.
