276 citations · 433 across the 16 of their papers we have counts for
18 papers
TaintRadar: Semantic-Aware Taint-Style Vulnerability Detection via Augmented Code Property Graphs
Elie Rizk, Firas Ben Hmida, Birhanu Eshete
Despite significant advances, static vulnerability analysis suffers from three critical limitations: coarse sanitization modeling, which treats validation as a binary barrier; data…
NeuroTrace: Inference Provenance-Based Detection of Adversarial Examples
Firas Ben Hmida, Philemon Hailemariam, Kashif Ali Khan +1
Deep neural networks (DNNs) remain largely opaque at inference time, limiting our ability to detect and diagnose malicious input manipulations such as adversarial examples. Existin…
DeepLeak: Privacy Enhancing Hardening of Model Explanations Against Membership Leakage
Firas Ben Hmida, Zain Sbeih, Philemon Hailemariam +1
Machine learning (ML) explainability is central to algorithmic transparency in high-stakes settings such as predictive diagnostics and loan approval. However, these same domains re…
DeepProv: Behavioral Characterization and Repair of Neural Networks via Inference Provenance Graph Analysis
Firas Ben Hmida, Abderrahmen Amich, Ata Kaboudi +1
Deep neural networks (DNNs) are increasingly being deployed in high-stakes applications, from self-driving cars to biometric authentication. However, their unpredictable and unreli…
Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution Detection
Abderrahmen Amich, Ata Kaboudi, Birhanu Eshete
Evasion attacks against machine learning models often succeed via iterative probing of a fixed target model, whereby an attack that succeeds once will succeed repeatedly. One promi…
MIAShield: Defending Membership Inference Attacks via Preemptive Exclusion of Members
Ismat Jarin, Birhanu Eshete
In membership inference attacks (MIAs), an adversary observes the predictions of a model to determine whether a sample is part of the model's training data. Existing MIA defenses c…
Rethinking Machine Learning Robustness via its Link with the Out-of-Distribution Problem
Abderrahmen Amich, Birhanu Eshete
Despite multiple efforts made towards robust machine learning (ML) models, their vulnerability to adversarial examples remains a challenging problem that calls for rethinking the d…
DP-UTIL: Comprehensive Utility Analysis of Differential Privacy in Machine Learning
Ismat Jarin, Birhanu Eshete
Differential Privacy (DP) has emerged as a rigorous formalism to reason about quantifiable privacy leakage. In machine learning (ML), DP has been employed to limit inference/disclo…
EG-Booster: Explanation-Guided Booster of ML Evasion Attacks
Abderrahmen Amich, Birhanu Eshete
The widespread usage of machine learning (ML) in a myriad of domains has raised questions about its trustworthiness in security-critical environments. Part of the quest for trustwo…
Morphence: Moving Target Defense Against Adversarial Examples
Abderrahmen Amich, Birhanu Eshete
Robustness to adversarial examples of machine learning models remains an open topic of research. Attacks often succeed by repeatedly probing a fixed target model with adversarial e…
Explanation-Guided Diagnosis of Machine Learning Evasion Attacks
Abderrahmen Amich, Birhanu Eshete
Machine Learning (ML) models are susceptible to evasion attacks. Evasion accuracy is typically assessed using aggregate evasion rate, and it is an open question whether aggregate e…
PRICURE: Privacy-Preserving Collaborative Inference in a Multi-Party Setting
Ismat Jarin, Birhanu Eshete
When multiple parties that deal with private data aim for a collaborative prediction task such as medical image classification, they are often constrained by data protection regula…
Best-Effort Adversarial Approximation of Black-Box Malware Classifiers
Abdullah Ali, Birhanu Eshete
An adversary who aims to steal a black-box model repeatedly queries the model via a prediction API to learn a function that approximates its decision boundary. Adversarial approxim…
POIROT: Aligning Attack Behavior with Kernel Audit Records for Cyber Threat Hunting
Sadegh M. Milajerdi, Birhanu Eshete, Rigel Gjomemo +1
Cyber threat intelligence (CTI) is being used to search for indicators of attacks that might have compromised an enterprise network for a long time without being discovered. To hav…
ProPatrol: Attack Investigation via Extracted High-Level Tasks
Sadegh M. Milajerdi, Birhanu Eshete, Rigel Gjomemo +1
Kernel audit logs are an invaluable source of information in the forensic investigation of a cyber-attack. However, the coarse granularity of dependency information in audit logs l…
HOLMES: Real-time APT Detection through Correlation of Suspicious Information Flows
Sadegh M. Milajerdi, Rigel Gjomemo, Birhanu Eshete +2
In this paper, we present HOLMES, a system that implements a new approach to the detection of Advanced and Persistent Threats (APTs). HOLMES is inspired by several case studies of…
SLEUTH: Real-time Attack Scenario Reconstruction from COTS Audit Data
Md Nahid Hossain, Sadegh M Milajerdi, Junao Wang +5
We present an approach and system for real-time reconstruction of attack scenarios on an enterprise host. To meet the scalability and real-time needs of the problem, we develop a p…
Attack Analysis Results for Adversarial Engagement 1 of the DARPA Transparent Computing Program
Birhanu Eshete, Rigel Gjomemo, Md Nahid Hossain +5
This report presents attack analysis results of the first adversarial engagement event stream for the first engagement of the DARPA TC program conducted in October 2016. The analys…