Manuel Egele

Manuel Egele

Auto-generated profile, based on publicly available information

Manuel Egele

Boston University, Boston, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 September 2018 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
OTOzan Tuncer
Ozan Tuncer
EAEmre Ates
Emre Ates
YZYijia Zhang
Yijia Zhang
ATAta Turk
Ata Turk
JBJim Brandt
Jim Brandt
ACAyse K. Coskun
Ayse K. Coskun
As the size and complexity of HPC systems grow in line with advancements in hardware and software technology, HPC systems increasingly suffer from performance variation due to shared resource contention as well as software- and hardware-related problems. Such performance variations can lead to failures and inefficiencies, and are among the main challenges in system resiliency. To minimize the impact of performance variation, one must quickly and accurately detect and diagnose the anomalies that cause the variation and take mitigating actions. However, it is difficult to identify anomalies based on the voluminous, high-dimensional, and noisy data collected by system monitoring infrastructures. This paper presents a novel machine learning based framework to automatically diagnose performance anomalies at runtime. Our framework leverages historical resource usage data to extract signatures of previously-observed anomalies. We first convert the collected time series data into easy-to-compute statistical features. We then identify the features that are required to detect anomalies, and extract the signatures of these anomalies. At runtime, we use these signatures to diagnose anomalies with negligible overhead. We evaluate our framework using experiments on a real-world HPC supercomputer and demonstrate that our approach successfully identifies 98% of injected anomalies and consistently outperforms existing anomaly diagnosis techniques.

11 November 2023
Verified
Conference Paper
Open access
BABurak Aksar
Burak Aksar
ESEfe Sencan
Efe Sencan
BSBenjamin Schwaller
Benjamin Schwaller
OAOmar Aaziz
Omar Aaziz
VLVitus J. Leung
Vitus J. Leung
ACAyse K. Coskun
Ayse K. Coskun
Performance variations caused by anomalies in modern High Performance Computing (HPC) systems lead to decreased efficiency, impaired application performance, and increased operational costs. While machine learning (ML)-based frameworks for automated anomaly detection (often based on time series telemetry data) are gaining popularity in the literature, practical deployment challenges are often overlooked. Some ML-based frameworks require extensive customization, while others need a rich set of labeled samples, none of which are feasible for a production HPC system. This paper introduces a variational autoencoder-based anomaly detection framework, Prodigy, that outperforms the state-of-the-art alternatives by achieving a 0.95 F1-score when detecting performance anomalies. The paper also provides a real system implementation of Prodigy that enables easy integration with monitoring frameworks and rapid deployment. We deploy Prodigy on a production HPC system and demonstrate 88% accuracy in detecting anomalies. Prodigy involves an interface to provide job- and node-level analysis and explanations for anomaly predictions.

18 December 2017 in IEEE Computer Architecture Letters
Verified
Journal Article
Open access
LDLeila Delshadtehrani
Leila Delshadtehrani
SESchuyler Eldridge
Schuyler Eldridge
SCSadullah Canakci
Sadullah Canakci
MEManuel Egele
Manuel Egele
AJAjay Joshi
Ajay Joshi
Researchers widely employ hardware performance counters (HPCs) as well as debugging and profiling tools in processors for monitoring different events such as cache hits, cache misses, and branch prediction statistics during the execution of programs. The collected information can be used for power, performance, and thermal management of the system as well as detecting anomalies or malicious behavior in the software. However, monitoring new or complex events using HPCs and existing tools is a challenging task because HPCs only provide a fixed pool of raw events to monitor. To address this challenge, we propose the implementation of a programmable hardware monitor in a complete system framework including the hardware monitor architecture and its interface with an in-order single-issue RISC-V processor as well as an operating system. As a proof of concept, we demonstrate how to programmatically implement a shadow stack using our hardware monitor and how the programmed shadow stack detects stack buffer overflow attacks. Our hardware monitor design incurs a 26% power overhead and a 15% area overhead over an unmodified RISC-V processor. Our programmed shadow stack has less than 3% performance overhead in the worst case.

13 February 2024 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
BABurak Aksar
Burak Aksar
ESEfe Sencan
Efe Sencan
BSBenjamin Schwaller
Benjamin Schwaller
OAOmar Aaziz
Omar Aaziz
VLVitus J. Leung
Vitus J. Leung
ACAyse K. Coskun
Ayse K. Coskun
With the increasing scale and complexity of High-Performance Computing (HPC) systems, performance variations in applications caused by anomalies have become significant bottlenecks in system health and operational efficiency. As we move towards exascale systems, these variations become more prominent due to the increased sharing of resources. Such variations lead to lower energy efficiency and higher operational costs. To mitigate these problems, one must quickly and accurately diagnose the root cause of the anomalies at scale. One way to evaluate system health and identify the underlying causes is by manually examining certain performance metrics in telemetry data or using rule-based methods. Due to the daily size of telemetry data reaching terabytes and the fact that the numeric telemetry data contains thousands of metrics, manual analysis of telemetry to diagnose problems becomes challenging. Given these limitations, Machine Learning (ML)-based approaches have been gaining popularity as they have been shown to be effective and practical in diagnosing previously encountered performance anomalies. One primary challenge for supervised ML models is that they require a significant amount of labeled samples during training. However, obtaining many labels for anomalies is extremely difficult and costly, considering anomalies occur infrequently and real-world numeric system telemetry data is hard to label since it contains thousands of metrics. This paper proposes a novel active learning-based framework that diagnoses performance anomalies (i.e., identifying the type of an anomaly) in HPC systems at runtime using significantly fewer labeled samples compared to state-of-the-art ML-based approaches. We show that the proposed framework achieves the same F1-score compared to a supervised approach using much fewer labeled samples (i.e., 16x fewer samples for achieving a 0.78 F1-score, 11x fewer samples for achieving a 0.82 F1-score), even when there are previously unseen applications and application inputs in the test dataset.

9 July 2022 in ACM Transactions on Privacy and Security
Verified
Journal Article
Open access
WBWilliam Blair
William Blair
AMAndrea Mambretti
Andrea Mambretti
SASajjad Arshad
Sajjad Arshad
MWMichael Weissbacher
Michael Weissbacher
WRWilliam Robertson
William Robertson
MEManuel Egele
Manuel Egele
Fuzz testing repeatedly assails software with random inputs in order to trigger unexpected program behaviors, such as crashes or timeouts, and has historically revealed serious security vulnerabilities. In this article, we present HotFuzz, a framework for automatically discovering Algorithmic Complexity (AC) time and space vulnerabilities in Java libraries. HotFuzz uses micro-fuzzing, a genetic algorithm that evolves arbitrary Java objects in order to trigger the worst-case performance for a method under test. We define Small Recursive Instantiation (SRI) as a technique to derive seed inputs represented as Java objects to micro-fuzzing. After micro-fuzzing, HotFuzz synthesizes test cases that triggered AC vulnerabilities into Java programs and monitors their execution in order to reproduce vulnerabilities outside the fuzzing framework. HotFuzz outputs those programs that exhibit high resource utilization as witnesses for AC vulnerabilities in a Java library. We evaluate HotFuzz over the Java Runtime Environment (JRE), the 100 most popular Java libraries on Maven, and challenges contained in the DARPA Space and Time Analysis for Cybersecurity (STAC) program. We evaluate SRI’s effectiveness by comparing the performance of micro-fuzzing with SRI, measured by the number of AC vulnerabilities detected, to simply using empty values as seed inputs. In this evaluation, we verified known AC vulnerabilities, discovered previously unknown AC vulnerabilities that we responsibly reported to vendors, and received confirmation from both IBM and Oracle. Our results demonstrate that micro-fuzzing finds AC vulnerabilities in real-world software, and that micro-fuzzing with SRI-derived seed inputs outperforms using empty values in both the temporal and spatial domains.