activity
20242026
most citedGenerative AI like ChatGPT in Blockchain Federated Learning: use cases, opportunities and future

2 citations · 3 across the 17 of their papers we have counts for

collaborators

12 papers

cs.CR2026

Influence Is Not Authority: When Causal Guardrail Signals Make Legitimate Tool Use Look Like an Attack in Tool-Using LLM Agents

Tanzim Ahad, Ismail Hossain, Md Jahangir Alam +3

The key limitation of current state-of-the-art influence-based guardrails is that they do not reliably distinguish a legitimate, user-authorized action from a malicious, unauthoriz…

cs.CR2026

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

Ismail Hossain, Sai Puppala, Md Jahangir Alam +2

Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely u…

cs.CR2026

Semantic Intent Fragmentation: A Single-Shot Compositional Attack on Multi-Agent AI Pipelines

Tanzim Ahad, Ismail Hossain, Md Jahangir Alam +4

We introduce Semantic Intent Fragmentation (SIF), an attack class against LLM orchestration systems where a single, legitimately phrased request causes an orchestrator to decompose…

cs.LG2026

When Safety Geometry Collapses: Fine-Tuning Vulnerabilities in Agentic Guard Models

Ismail Hossain, Sai Puppala, Jannatul Ferdaus +4

A guard model fine-tuned on entirely benign data can lose all safety alignment -- not through adversarial manipulation, but through standard domain specialization. We demonstrate t…

cs.CR2026

Agent-Fence: Mapping Security Vulnerabilities Across Deep Research Agents

Sai Puppala, Ismail Hossain, Md Jahangir Alam +5

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsaf…

cs.LG2025

Real-Time Personalized Content Adaptation through Matrix Factorization and Context-Aware Federated Learning

Sai Puppala, Ismail Hossain, Md Jahangir Alam +1

Our study presents a multifaceted approach to enhancing user interaction and content relevance in social media platforms through a federated learning framework. We introduce person…