105 citations · 155 across the 11 of their papers we have counts for
11 papers
A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models
Hamid Kazemi, Atoosa Chegini, Maria Safi
Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons tha…
Reasoning's Razor: Reasoning Improves Accuracy but Can Hurt Recall at Critical Operating Points in Safety and Hallucination Detection
Atoosa Chegini, Hamid Kazemi, Garrett Souza +5
Reasoning has become a central paradigm for large language models (LLMs), consistently boosting accuracy across diverse benchmarks. Yet its suitability for precision-sensitive task…
SALSA: Soup-based Alignment Learning for Stronger Adaptation in RLHF
Atoosa Chegini, Hamid Kazemi, Iman Mirzadeh +5
In Large Language Model (LLM) development, Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning models with human values and preferences. RLHF traditionally re…
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
Abhimanyu Hans, Yuxin Wen, Neel Jain +8
Large language models can memorize and repeat their training data, causing privacy and copyright risks. To mitigate memorization, we introduce a subtle modification to the next-tok…
Generating Potent Poisons and Backdoors from Scratch with Guided Diffusion
Hossein Souri, Arpit Bansal, Hamid Kazemi +7
Modern neural networks are often trained on massive datasets that are web scraped with minimal human inspection. As a result of this insecure curation pipeline, an adversary can po…
What do we learn from inverting CLIP models?
Hamid Kazemi, Atoosa Chegini, Jonas Geiping +2
We employ an inversion-based approach to examine CLIP models. Our examination reveals that inverting CLIP models results in the generation of images that exhibit semantic alignment…
Spotting LLMs With Binoculars: Zero-Shot Detection of Machine-Generated Text
Abhimanyu Hans, Avi Schwarzschild, Valeriia Cherepanova +5
Detecting text generated by modern large language models is thought to be hard, as both LLMs and humans can exhibit a wide range of complex behaviors. However, we find that a score…
What do Vision Transformers Learn? A Visual Exploration
Amin Ghiasi, Hamid Kazemi, Eitan Borgnia +5
Vision transformers (ViTs) are quickly becoming the de-facto architecture for computer vision, yet we understand very little about why they work and what they learn. While existing…
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
Yuxin Wen, Arpit Bansal, Hamid Kazemi +4
As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data…
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
Arpit Bansal, Eitan Borgnia, Hong-Min Chu +6
Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative beh…
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data Augmentations
Amin Ghiasi, Hamid Kazemi, Steven Reich +3
Existing techniques for model inversion typically rely on hard-to-tune regularizers, such as total variation or feature regularization, which must be individually calibrated for ea…