5 papers
Faithful or Fabricated? A Causal Framework for Rationalization Bias in LLM Judges
Riya Tapwal, Abhishek Kumar, Carsten Maple
Large language models (LLMs) are increasingly used as automatic judges for summarization and dialogue evaluation. Prior work has documented biases such as position, verbosity, and…
PRISM: Generation-Time Detection and Mitigation of Secret Leakage in Multi-Agent LLM Pipelines
Riya Tapwal, Abhishek Kumar, Carsten Maple
Multi-agent LLM systems introduce a security risk in which sensitive information accessed by one agent can propagate through shared context and reappear in downstream outputs, even…
Field-Localized Forgery Detection for Digital Identity Documents
Abhishek Kumar, Riya Tapwal, Carsten Maple +1
Digital onboarding and eKYC systems used by banks, fintech platforms, telecom providers, and other third-party services commonly verify users by comparing an uploaded identity docu…
Single-Configuration Attack Success Rate Is Not Enough: Jailbreak Evaluations Should Report Distributional Attack Success
Carsten Maple, Abhishek Kumar, Riya Tapwal
Many jailbreak attack research papers report attack success rates for a limited number of parameter settings, even though there are many combinations of parameter settings that cou…
DriveSafe: A Hierarchical Risk Taxonomy for Safety-Critical LLM-Based Driving Assistants
Abhishek Kumar, Riya Tapwal, Carsten Maple
Large Language Models (LLMs) are increasingly integrated into vehicle-based digital assistants, where unsafe, ambiguous, or legally incorrect responses can lead to serious safety,…