7 papers
Covert Trait Propagation Is Representation Alignment: Mechanistic Evidence from Hidden-Channel Distillation
Kargi Chauhan, Aditya Shah
A student model trained on pure uniform noise can still inherit its teacher's digit-classification ability, provided the two share initialization. Previous work proves this transfe…
MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents
Pratibha Revankar, Kargi Chauhan, Jihye Kim +3
When LLM agents are coerced into covertly encoding sensitive data (Base64, ROT13, acrostic, synonym chains, and beyond), the resulting outputs evade output-side detection but the u…
When Does Structure Help? The Information Bonus of AlphaFold2 Representations over Protein Language Models
Kargi Chauhan
AI scientist systems increasingly choose biological foundation models before they choose experiments. In protein pipelines, this creates a concrete engineering and scientific quest…
Dead Science Walking: Publication Bias and the AI Scientist Pipeline
Kargi Chauhan
AI scientist systems are beginning to automate the production, evaluation, and iteration of scientific hypotheses. Their promise is speed; their risk is that speed also scales erro…
Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents
Kargi Chauhan, Pratibha Revankar
LLM agents often place sensitive credentials in the same context window as untrusted retrieved content, creating a direct path for indirect prompt injection to induce credential ex…
UCSC-NLP at SemEval-2026 Task 13: Multi-View Generalization and Diagnostic Analysis of Machine-Generated Code Detection
Kargi Chauhan, Sadiba Nusrat Nur
With the rapid growth of large language models for code generation, distinguishing between human-written and AI-generated code has become increasingly critical for academic integri…