collaborators

9 papers

cs.AI2026

MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study

Tim Van hamme, Thomas Vissers, Javier Carnerero-Cano +4

LLMs are increasingly deployed as autonomous agents with access to tools, databases, and external services, yet practitioners (across different sectors) lack systematic methods to…

cs.LG2026

CLaRE-ty Amid Chaos: Quantifying Representational Entanglement to Predict Ripple Effects in LLM Editing

Manit Baser, Alperen Yildiz, Dinil Mon Divakaran +1

The static knowledge representations of large language models (LLMs) inevitably become outdated or incorrect over time. While model-editing techniques offer a promising solution by…

cs.LG2026

ThinkEval: Practical Evaluation of Knowledge Leakage in LLM Editing using Thought-based Knowledge Graphs

Manit Baser, Dinil Mon Divakaran, Mohan Gurusamy

Robust model-editing techniques are essential for deploying large language models (LLMs) in practical applications, as they enable cost-effective ways to deal with challenges such…

cs.CR2025

AI-based Traffic Modeling for Network Security and Privacy: Challenges Ahead

Dinil Mon Divakaran

Network traffic analysis using AI (machine learning and deep learning) models made significant progress over the past decades. Traffic analysis addresses various challenging proble…

cs.CR2025

RECTor: Robust and Efficient Correlation Attack on Tor

Binghui Wu, Dinil Mon Divakaran, Levente Csikor +1

Tor is a widely used anonymity network that conceals user identities by routing traffic through encrypted relays, yet it remains vulnerable to traffic correlation attacks that dean…

cs.CR2025

UniNet: A Unified Multi-granular Traffic Modeling Framework for Network Security

Binghui Wu, Dinil Mon Divakaran, Mohan Gurusamy

As modern networks grow increasingly complex--driven by diverse devices, encrypted protocols, and evolving threats--network traffic analysis has become critically important. Existi…