Search Results for author:
Found 9 papers, 5 papers with code
PalmBench: A Comprehensive Benchmark of Compressed Large Language Models on Mobile Platforms
Deploying large language models (LLMs) locally on mobile devices is advantageous in scenarios where transmitting data to remote cloud servers is either undesirable due to privacy concerns or impractical due to network connection.
A Study of Backdoors in Instruction Fine-tuned Language Models
Backdoor data poisoning, inserted within instruction examples used to fine-tune a foundation Large Language Model (LLM) for downstream tasks (\textit{e. g.,} sentiment prediction), is a serious security concern due to the evasive nature of such attacks.
Stratified Adversarial Robustness with Rejection
We theoretically analyze the stratified rejection setting and propose a novel defense method -- Adversarial Training with Consistent Prediction-based Rejection (CPR) -- for building a robust selective classifier.
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
foundation models) has recently become a prevalent learning paradigm, where one first pre-trains a representation using large-scale unlabeled data, and then learns simple predictors on top of the representation using small labeled data from the downstream tasks.
Concept-based Explanations for Out-Of-Distribution Detectors
Based on these metrics, we propose an unsupervised framework for learning a set of concepts that satisfy the desired properties of high detection completeness and concept separability, and demonstrate its effectiveness in providing concept-based explanations for diverse off-the-shelf OOD detectors.
Revisiting Adversarial Robustness of Classifiers With a Reject Option
Motivated by this metric, we propose novel loss functions and a robust training method -- \textit{stratified adversarial training with rejection} (SATR) -- for a classifier with reject option, where the goal is to accept and correctly-classify small input perturbations, while allowing the rejection of larger input perturbations that cannot be correctly classified.
Fast and Sample-Efficient Domain Adaptation for Autoencoder-Based End-to-End Communication
In this paper, we address the setting where the target domain has only limited labeled data from a distribution that is expected to change frequently.
Few-Shot Domain Adaptation For End-to-End Communication
The problem of end-to-end learning of a communication system using an autoencoder -- consisting of an encoder, channel, and decoder modeled using neural networks -- has recently been shown to be an effective approach.
A General Framework For Detecting Anomalous Inputs to DNN Classifiers
We propose an unsupervised anomaly detection framework based on the internal DNN layer representations in the form of a meta-algorithm with configurable components.
