42 citations · 207 across the 76 of their papers we have counts for
82 papers
Caching Policies based on Object Sizes
Ridwanul Hasan Tanvir, George Kesidis
We evaluate eviction policies that consider the lengths of the objects being cached for different cache sizes (cost) and different workloads. Workloads include the Independent Refe…
Performance and Cost-Aware Cache Provisioning
Ridwanul Tanvir, George Kesidis
While traditional cache policy evaluations fix capacity - often at 0.1% of the dataset - and measure the resulting hit rate, practical edge-cloud deployments require balancing both…
CSO-LLM: Class Subspace Orthogonalization for Post-Training Backdoor Detection and Trigger Inversion in LLMs
Zhengxing Li, David J. Miller, Guangmingmei Yang +1
While post-training backdoor detection and trigger inversion schemes have been developed for AIs used e.g. for images, there is a paucity of such methods for LLMs. First, the LLM i…
A Novel Latent-Class Attack and its Detection by Class Subspace Orthogonalization
Guangmingmei Yang, David J. Miller, George Kesidis
Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks and backdoors (Trojans). In…
Improving the Sensitivity of Backdoor Detectors via Class Subspace Orthogonalization
Guangmingmei Yang, David J. Miller, George Kesidis
Most post-training backdoor detection methods rely on attacked models exhibiting extreme outlier detection statistics for the target class of an attack, compared to non-target clas…
Inverting Trojans in LLMs
Zhengxing Li, Guangmingmei Yang, Jayaram Raghuram +2
While effective backdoor detection and inversion schemes have been developed for AIs used e.g. for images, there are challenges in "porting" these methods to LLMs. First, the LLM i…
Fundamentals of Caching Layered Data objects
Agrim Bari, Gustavo de Veciana, George Kesidis
The effective management of large amounts of data processed or required by today's cloud or edge computing systems remains a fundamental challenge. This paper focuses on cache mana…
Understanding and Rectifying Safety Perception Distortion in VLMs
Xiaohan Zou, Jian Kang, George Kesidis +1
Recent studies reveal that vision-language models (VLMs) become more susceptible to harmful requests and jailbreak attacks after integrating the vision modality, exhibiting greater…
Ten Ways in which Virtual Reality Differs from Video Streaming
Gustavo de Veciana, Sonia Fahmy, George Kesidis +1
Virtual Reality (VR) applications have a number of unique characteristics that set them apart from traditional video streaming. These characteristics have major implications on the…
A Study of Backdoors in Instruction Fine-tuned Language Models
Jayaram Raghuram, George Kesidis, David J. Miller
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),…
CEPA: Consensus Embedded Perturbation for Agnostic Detection and Inversion of Backdoors
Guangmingmei Yang, Xi Li, Hang Wang +2
A variety of defenses have been proposed against Trojans planted in (backdoor attacks on) deep neural network (DNN) classifiers. Backdoor-agnostic methods seek to reliably detect a…
GPU Cluster Scheduling for Network-Sensitive Deep Learning
Aakash Sharma, Vivek M. Bhasi, Sonali Singh +3
We propose a novel GPU-cluster scheduler for distributed DL (DDL) workloads that enables proximity based consolidation of GPU resources based on the DDL jobs' sensitivities to the…
Post-Training Overfitting Mitigation in DNN Classifiers
Hang Wang, David J. Miller, George Kesidis
Well-known (non-malicious) sources of overfitting in deep neural net (DNN) classifiers include: i) large class imbalances; ii) insufficient training-set diversity; and iii) over-tr…
Backdoor Mitigation by Correcting the Distribution of Neural Activations
Xi Li, Zhen Xiang, David J. Miller +1
Backdoor (Trojan) attacks are an important type of adversarial exploit against deep neural networks (DNNs), wherein a test instance is (mis)classified to the attacker's target clas…
Improved Activation Clipping for Universal Backdoor Mitigation and Test-Time Detection
Hang Wang, Zhen Xiang, David J. Miller +1
Deep neural networks are vulnerable to backdoor attacks (Trojans), where an attacker poisons the training set with backdoor triggers so that the neural network learns to classify t…
Temporal-Distributed Backdoor Attack Against Video Based Action Recognition
Xi Li, Songhe Wang, Ruiquan Huang +2
Deep neural networks (DNNs) have achieved tremendous success in various applications including video action recognition, yet remain vulnerable to backdoor attacks (Trojans). The ba…
Training set cleansing of backdoor poisoning by self-supervised representation learning
H. Wang, S. Karami, O. Dia +6
A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small numbe…
Analysis of Distributed Deep Learning in the Cloud
Aakash Sharma, Vivek M. Bhasi, Sonali Singh +6
We aim to resolve this problem by introducing a comprehensive distributed deep learning (DDL) profiler, which can determine the various execution "stalls" that DDL suffers from whi…
Cluster Resource Management for Dynamic Workloads by Online Optimization
Nader Alfares, George Kesidis, Ata Fatahi Baarzi +1
Over the past ten years, many different approaches have been proposed for different aspects of the problem of resources management for long running, dynamic and diverse workloads s…
MM-BD: Post-Training Detection of Backdoor Attacks with Arbitrary Backdoor Pattern Types Using a Maximum Margin Statistic
Hang Wang, Zhen Xiang, David J. Miller +1
Backdoor attacks are an important type of adversarial threat against deep neural network classifiers, wherein test samples from one or more source classes will be (mis)classified t…
Post-Training Detection of Backdoor Attacks for Two-Class and Multi-Attack Scenarios
Zhen Xiang, David J. Miller, George Kesidis
Backdoor attacks (BAs) are an emerging threat to deep neural network classifiers. A victim classifier will predict to an attacker-desired target class whenever a test sample is emb…
Test-Time Detection of Backdoor Triggers for Poisoned Deep Neural Networks
Xi Li, Zhen Xiang, David J. Miller +1
Backdoor (Trojan) attacks are emerging threats against deep neural networks (DNN). A DNN being attacked will predict to an attacker-desired target class whenever a test sample from…
Detecting Backdoor Attacks Against Point Cloud Classifiers
Zhen Xiang, David J. Miller, Siheng Chen +2
Backdoor attacks (BA) are an emerging threat to deep neural network classifiers. A classifier being attacked will predict to the attacker's target class when a test sample from a s…
Backdoor Attack and Defense for Deep Regression
Xi Li, George Kesidis, David J. Miller +1
We demonstrate a backdoor attack on a deep neural network used for regression. The backdoor attack is localized based on training-set data poisoning wherein the mislabeled samples…