4 papers
Backdoors Leave Structural Traces: FedMAST for Backdoor Detection and Containment in Federated Learning
Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan
Federated learning enables distributed training without requiring clients to share their raw data. However, its reliance on the integrity of the client-submitted updates exposes th…
Beyond Unsafe Detection: Counterfactually Anchored Evidence Attribution for Multi-Turn LLM Safety Failures
Srinivasan Subramanian, Kazi Aminul Islam, Md. Abdullah Al Hafiz Khan
As Large Language Models (LLMs) move from conversational assistants to advanced agentic systems, guardrail failures can convert adversarial intents into harmful executions. However…
TRACE: A Multi-Layer Benchmark for Human AI Controller Coordination Under Drift and Failure
Joshua Zuniga, Srinivasan Subramanian, Ramya Madhuri Narapureddy +1
Modern cyber-physical and AI-assisted systems couple human operators, AI decision modules, and automated controllers in a single control loop, so trustworthiness depends on the who…
Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning
Srinivasan Subramanian, Md. Abdullah Al Hafiz Khan, Kazi Aminul Islam
Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior. Distance-based aggregation rules, such as Krum and Multi-Kru…