Manan Suri

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

Amine Lbath, Manan Suri, Aurélien Delaitre, Vadim Okun et autres

Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available agents can already aid attackers, who only need to find one exploitable weakness, while defenders must continuously identify and patch …

CyberForge: Verified Vulnerability Injection at Repository Level for Cybersecurity Agent Training

Amine Lbath, Manan Suri, Aurélien Delaitre, Vadim Okun et autres

Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world software. Generally available agents can already aid attackers, who only need to find one exploitable weakness, while defenders must continuously identify and patch …

fr, us (code pays fourni par la source)

Investigation of EM Fault Injection on Emerging Lightweight Neural Network Hardware

B.C. Goswami, Reejit Chetry, Chithambara Moorthii J, Manan Suri

in (code pays fourni par la source)

Variation-Aware Demonstration and Optimization of Block Floating Point and Integer Neural Network Acceleration on RRAM Compute in-Memory Hardware

Ahmed Sayed Shaban, Shreshtha Gothalyan, Manan Suri, Tuo‐Hung Hou

In this work, we propose a device-circuit-system co-design approach to achieve the best performance from a given variation-prone resistive random access memory (RRAM) compute-in-memory (CIM) hardware for deep neural network (DNN) acceleration and also demonstrate an optimized hardware implementation of block floating …

in, tw (code pays fourni par la source)

SIMMAC: SRAM IMC-Based Multibit Multiplication With Analog Carry Computation

Chithambara Moorthii J, Richa Mishra, Harshit Bansal, Sounak Dey et autres

Several applications, ranging from artificial intelligence to encryption, require dense multi-bit matrix multiplications. With the advent of big-data applications and edge deployment, a recent paradigm shift focuses on energy-efficient computation methodologies such as In-Memory Computing (IMC). In this work, we propose SRAM …

in (code pays fourni par la source)

Novel staggered quantum well design and in-surfactant GaN buffer layer in UVA light emitting diode heterostructures

Nor Syafiqah Azmi, Manan Suri, Mohd Ann Amirul Zulffiqal Md Sahar, Mohd Anas Ahmad et autres

my (code pays fourni par la source)

DNA-CIM: DNA Sequence Analysis Using RRAM-Based Compute In-Memory Accelerator

Chithambara Moorthii, Anmol Singla, Manan Suri

DNA sequence matching and mutation analysis are critical computational methods used in modern genomics, with applications ranging from identifying genetic disorders to under-standing evolutionary relationships. Moreover, understanding the functional effects of genetic modifications through mutation analysis can help in understanding disease mechanisms, …

in (code pays fourni par la source)

GRU-RVCIM: Efficient Implementation of Gated Recurrent Unit in RISC-V - Compute In Memory co-designed for Edge Applications

Chithambara Moorthii J, Arun M. George, Dighanchal Banerjee, Sounak Dey et autres

Gated Recurrent Unit (GRU) is a frequently employed variant of recurrent neural networks (RNNs) that is intended to reduce computational complexity and capture temporal dependencies in sequential data. GRUs have garnered significant traction in edge computing applications, including speech recognition, anomaly detection, …

in (code pays fourni par la source)

Investigation of Security Vulnerabilities in NVM-Based Persistent TinyML Hardware

B.C. Goswami, Chithambara Moorthii J, Harshit Bansal, Ayan Sajwan et autres

This study investigates vulnerabilities of future generation nonvolatile memory (NVM)-backed persistent TinyML hardware neural networks to side-channel attacks (SCAs) using electromagnetic (EM) analysis methods. We trained three different tinyML models: MobileNet, ResNet, and EfficientNet on three different standard datasets: F-MNIST, CIFAR-10, and …

in (code pays fourni par la source)

x-RAGE: eXtended Reality -- Action & Gesture Events Dataset

Vivek Parmar, Dwijay Bane, Syed Shakib Sarwar, Kleber Stangherlin et autres

With the emergence of the Metaverse and focus on wearable devices in the recent years gesture based human-computer interaction has gained significance. To enable gesture recognition for VR/AR headsets and glasses several datasets focusing on egocentric i.e. first-person view have emerged in …

Emerging non-volatile memory (NVM) technologies based nano-oscillators: Materials to applications

Manoj Kumar, Manan Suri

This comprehensive study provides a detailed review toward ongoing research on emerging non-volatile memory technologies based nano-oscillators, i.e., from the perspective of materials to applications. Depending on the materials used to fabricate them, the whole class of emerging nano-oscillators has been broadly …

de, in (code pays fourni par la source)

Non-Invasive Qualitative Vibration Analysis using Event Camera

Dwijay Bane, Anurag Gupta, Manan Suri

This technical report investigates the application of event-based vision sensors in non-invasive qualitative vibration analysis, with a particular focus on frequency measurement and motion magnification. Event cameras, with their high temporal resolution and dynamic range, offer promising capabilities for real-time structural assessment …