Search Results for author:
Found 9 papers, 2 papers with code
SoK: Memorization in General-Purpose Large Language Models
A major part of this success is due to their huge training datasets and the unprecedented number of model parameters, which allow them to memorize large amounts of information contained in the training data.
On the Importance of Architecture and Feature Selection in Differentially Private Machine Learning
The use of differentially private learning algorithms in a "drop-in" fashion -- without accounting for the impact of differential privacy (DP) noise when choosing what feature engineering operations to use, what features to select, or what neural network architecture to use -- yields overly complex and poorly performing models.
Attacks as Defenses: Designing Robust Audio CAPTCHAs Using Attacks on Automatic Speech Recognition Systems
We begin by comparing 20 recent attack papers, classifying and measuring their suitability to serve as the basis of new "robust to transcription" but "easy for humans to understand" CAPTCHAs.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Enhanced Membership Inference Attacks against Machine Learning Models
Membership inference attacks are used as an auditing tool to quantify this leakage.
Covert Message Passing over Public Internet Platforms Using Model-Based Format-Transforming Encryption
We introduce a new type of format-transforming encryption where the format of ciphertexts is implicitly encoded within a machine-learned generative model.
Demystifying Limited Adversarial Transferability in Automatic Speech Recognition Systems
The targeted transferability of adversarial samples enables attackers to exploit black-box models in the real-world.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems
Like other systems based on neural networks, recent research has demonstrated that speech and speaker recognition systems are vulnerable to attacks using manipulated inputs.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Understanding Membership Inferences on Well-Generalized Learning Models
Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model.
Plausible Deniability for Privacy-Preserving Data Synthesis
We demonstrate the efficiency of this generative technique on a large dataset; it is shown to preserve the utility of original data with respect to various statistical analysis and machine learning measures.
