4 papers
PiSAs: Benchmarking Contextual Integrity in Multi-User Agentic Systems
Shubham Gupta, Nazanin Mohammadi Sepahvand, Abhinav Kumar +6
As LLM agents evolve from single-user assistants into shared organizational infrastructure, new privacy risks emerge: inappropriate information may not only be exposed through outp…
Detoxifying LLMs via Representation Erasure-Based Preference Optimization
Nazanin Mohammadi Sepahvand, Eleni Triantafillou, Hugo Larochelle +3
Large language models (LLMs) trained on webscale data can produce toxic outputs, raising concerns for safe deployment. Prior defenses, based on applications of DPO, NPO, and simila…
Leveraging Per-Instance Privacy for Machine Unlearning
Nazanin Mohammadi Sepahvand, Anvith Thudi, Berivan Isik +5
We present a principled, per-instance approach to quantifying the difficulty of unlearning via fine-tuning. We begin by sharpening an analysis of noisy gradient descent for unlearn…
BD-KD: Balancing the Divergences for Online Knowledge Distillation
Ibtihel Amara, Nazanin Sepahvand, Brett H. Meyer +2
We address the challenge of producing trustworthy and accurate compact models for edge devices. While Knowledge Distillation (KD) has improved model compression in terms of achievi…