206 citations · 246 across the 18 of their papers we have counts for
19 papers
A Systematic Methodology for Evaluating Failure Independence in LLM-Generated Code
Rodrigo Pato Nogueira, Karthik Pattabiraman, Marco Vieira +1
N-Version Programming (NVP) improves software reliability by executing multiple independent implementations and combining outputs, but its adoption is limited by high cost and the…
AIReSim: A Discrete Event Simulator for Large-scale AI Cluster Reliability Modeling
Karthik Pattabiraman, Mihir Patel, Fred Lin
Failures in clusters running large-scale AI workloads can result in decreased utilization. Because the cost of a failure in such AI workloads is high (as it requires restarting the…
RVDebloater: Mode-based Adaptive Firmware Debloating for Robotic Vehicles
Mohsen Salehi, Karthik Pattabiraman
As the number of embedded devices grows and their functional requirements increase, embedded firmware is becoming increasingly larger, thereby expanding its attack surface. Despite…
Anonymity Unveiled: A Practical Framework for Auditing Data Use in Deep Learning Models
Zitao Chen, Karthik Pattabiraman
The rise of deep learning (DL) has led to a surging demand for training data, which incentivizes the creators of DL models to trawl through the Internet for training materials. Mea…
AutoPatch: Automated Generation of Hotpatches for Real-Time Embedded Devices
Mohsen Salehi, Karthik Pattabiraman
Real-time embedded devices like medical or industrial devices are increasingly targeted by cyber-attacks. Prompt patching is crucial to mitigate the serious consequences of such at…
SpecGuard: Specification Aware Recovery for Robotic Autonomous Vehicles from Physical Attacks
Pritam Dash, Ethan Chan, Karthik Pattabiraman
Robotic Autonomous Vehicles (RAVs) rely on their sensors for perception, and follow strict mission specifications (e.g., altitude, speed, and geofence constraints) for safe and tim…
A Method to Facilitate Membership Inference Attacks in Deep Learning Models
Zitao Chen, Karthik Pattabiraman
Modern machine learning (ML) ecosystems offer a surging number of ML frameworks and code repositories that can greatly facilitate the development of ML models. Today, even ordinary…
Systematically Assessing the Security Risks of AI/ML-enabled Connected Healthcare Systems
Mohammed Elnawawy, Mohammadreza Hallajiyan, Gargi Mitra +2
The adoption of machine-learning-enabled systems in the healthcare domain is on the rise. While the use of ML in healthcare has several benefits, it also expands the threat surface…
Error Propagation Analysis for Multithreaded Programs: An Empirical Approach
Stefan Winter, Abraham Chan, Habib Saissi +2
Fault injection is a technique to measure the robustness of a program to errors by introducing faults into the program under test. Following a fault injection experiment, Error Pro…
ICS-Sniper: A Targeted Blackhole Attack on Encrypted ICS Traffic
Gargi Mitra, Chanyuan Liu, Pritam Dash +4
Modern industrial control systems (ICS) increasingly host their Supervisory Control and Data Acquisition (SCADA) services in the cloud to reduce the costs of large-scale automation…
Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction
Zitao Chen, Karthik Pattabiraman
Machine learning (ML) models are vulnerable to membership inference attacks (MIAs), which determine whether a given input is used for training the target model. While there have be…
Diagnosis-guided Attack Recovery for Securing Robotic Vehicles from Sensor Deception Attacks
Pritam Dash, Guanpeng Li, Mehdi Karimibiuki +1
Sensors are crucial for perception and autonomous operation in robotic vehicles (RV). Unfortunately, RV sensors can be compromised by physical attacks such as sensor tampering or s…
Characterizing and Improving the Resilience of Accelerators in Autonomous Robots
Deval Shah, Zi Yu Xue, Karthik Pattabiraman +1
Motion planning is a computationally intensive and well-studied problem in autonomous robots. However, motion planning hardware accelerators (MPA) must be soft-error resilient for…
Towards a Safety Case for Hardware Fault Tolerance in Convolutional Neural Networks Using Activation Range Supervision
Florian Geissler, Syed Qutub, Sayanta Roychowdhury +6
Convolutional neural networks (CNNs) have become an established part of numerous safety-critical computer vision applications, including human robot interactions and automated driv…
Jujutsu: A Two-stage Defense against Adversarial Patch Attacks on Deep Neural Networks
Zitao Chen, Pritam Dash, Karthik Pattabiraman
Adversarial patch attacks create adversarial examples by injecting arbitrary distortions within a bounded region of the input to fool deep neural networks (DNNs). These attacks are…
ReLUSyn: Synthesizing Stealthy Attacks for Deep Neural Network Based Cyber-Physical Systems
Aarti Kashyap, Syed Mubashir Iqbal, Karthik Pattabiraman +1
Cyber Physical Systems (cps) are deployed in many mission-critical settings, such as medical devices, autonomous vehicular systems and aircraft control management systems. As more…
How Effective are Smart Contract Analysis Tools? Evaluating Smart Contract Static Analysis Tools Using Bug Injection
Asem Ghaleb, Karthik Pattabiraman
Security attacks targeting smart contracts have been on the rise, which have led to financial loss and erosion of trust. Therefore, it is important to enable developers to discover…
TensorFI: A Flexible Fault Injection Framework for TensorFlow Applications
Zitao Chen, Niranjhana Narayanan, Bo Fang +3
As machine learning (ML) has seen increasing adoption in safety-critical domains (e.g., autonomous vehicles), the reliability of ML systems has also grown in importance. While prio…
A Low-cost Fault Corrector for Deep Neural Networks through Range Restriction
Zitao Chen, Guanpeng Li, Karthik Pattabiraman
The adoption of deep neural networks (DNNs) in safety-critical domains has engendered serious reliability concerns. A prominent example is hardware transient faults that are growin…