14 citations · 45 across the 37 of their papers we have counts for
10 papers · 1 filter
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…
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…
Benchmarking Security Risk Detection and Verification in Open Agentic Skill Ecosystems
Ismail Hossain, Sai Puppala, Zhuoran Lu +2
Open agent platforms allow community contributors to publish reusable skills that agents can invoke at runtime. This extensibility also creates a supply-chain risk: malicious contr…
The Misattribution Gap: When Memory Poisoning Looks Like Model Failure in Agentic AI Systems
Tanzim Ahad, Ismail Hossain, Md Jahangir Alam +3
Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Ga…
The Art of the Jailbreak: Formulating Jailbreak Attacks for LLM Security Beyond Binary Scoring
Ismail Hossain, Tanzim Ahad, Md Jahangir Alam +3
Jailbreak attacks -- adversarial prompts that bypass LLM alignment through purely linguistic manipulation -- pose a growing operational security threat, yet the field lacks large-s…
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…
Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization
Samrendra Roy, Kazuma Kobayashi, Souvik Chakraborty +2
Continual learning, the ability to acquire new tasks sequentially without forgetting prior knowledge, is essential for deploying neural networks in dynamic real-world environments,…
Neuromorphic Continual Learning for Sequential Deployment of Nuclear Plant Monitoring Systems
Samrendra Roy, Sajedul Talukder, Syed Bahauddin Alam
Anomaly detection in nuclear industrial control systems (ICS) requires continuous, energy-efficient monitoring across multiple subsystems that are often deployed at different stage…
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…
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…