8 papers
Verify Before You Fix: Agentic Execution Grounding for Trustworthy Cross-Language Code Analysis
Jugal Gajjar
Learned classifiers deployed in agentic pipelines face a fundamental reliability problem: predictions are probabilistic inferences, not verified conclusions, and acting on them wit…
Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?
Kamalasankari Subramaniakuppusamy, Jugal Gajjar
Post-hoc feature attribution methods are widely deployed in safety-critical vision systems, yet their stability under realistic input perturbations remains poorly characterized. Ex…
HyperComplEx: Adaptive Multi-Space Knowledge Graph Embeddings
Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy +1
Knowledge graphs have emerged as fundamental structures for representing complex relational data across scientific and enterprise domains. However, existing embedding methods face…
MLCPD: A Unified Multi-Language Code Parsing Dataset with Universal AST Schema
Jugal Gajjar, Kamalasankari Subramaniakuppusamy
We introduce the MultiLang Code Parser Dataset (MLCPD), a large-scale, language-agnostic dataset unifying syntactic and structural representations of code across ten major programm…
Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models
Jugal Gajjar, Kaustik Ranaware, Kamalasankari Subramaniakuppusamy
Software vulnerabilities remain a persistent risk, yet static and dynamic analyses often overlook structural dependencies that shape insecure behaviors. Viewing programs as heterog…
SecureFixAgent: A Hybrid LLM Agent for Automated Python Static Vulnerability Repair
Jugal Gajjar, Kamalasankari Subramaniakuppusamy, Relsy Puthal +1
Modern software development pipelines face growing challenges in securing large codebases with extensive dependencies. Static analysis tools like Bandit are effective at vulnerabil…