Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models
Reasoning models hide unsafe thoughts behind safe answers; we propose a metric DSAR to measure it and safety alignment method SARA to mitigate it.
Hijacking Large Language Models via Adversarial In-Context Learning
This work introduces a novel transferable attack against In-Context-Learning to hijack LLMs to generate the target response or jailbreak. We also propose a defense strategy …
Not all tokens are meant to be forgotten
This paper helps large language models forget sensitive and unwanted data without over-forgetting general data.
WalkGPT Grounded Vision-Language Conversation with Depth-Aware Segmentation for Pedestrian Navigation
rafi-ibn-sultan
Attention Smoothing Is All You Need For Unlearning
saleh-zare-zade
Collective Consent Who Needs to Consent to the Donation of Data Representing Multiple People?
emma-walquist
Automatic calibration for membership inference attack on large language models
saleh-zare-zade
Generative large language model—powered conversational ai app for personalized risk assessment Case study in covid-19
mohammad-amin-roshani