164 citations · 527 across the 37 of their papers we have counts for
7 papers · 1 filter
Effective Backdoor Mitigation in Vision-Language Models Depends on the Pre-training Objective
Sahil Verma, Gantavya Bhatt, Avi Schwarzschild +6
Despite the advanced capabilities of contemporary machine learning (ML) models, they remain vulnerable to adversarial and backdoor attacks. This vulnerability is particularly conce…
NEFTune: Noisy Embeddings Improve Instruction Finetuning
Neel Jain, Ping-yeh Chiang, Yuxin Wen +10
We show that language model finetuning can be improved, sometimes dramatically, with a simple augmentation. NEFTune adds noise to the embedding vectors during training. Standard fi…
Baseline Defenses for Adversarial Attacks Against Aligned Language Models
Neel Jain, Avi Schwarzschild, Yuxin Wen +7
As Large Language Models quickly become ubiquitous, it becomes critical to understand their security vulnerabilities. Recent work shows that text optimizers can produce jailbreakin…
A Cookbook of Self-Supervised Learning
Randall Balestriero, Mark Ibrahim, Vlad Sobal +16
Self-supervised learning, dubbed the dark matter of intelligence, is a promising path to advance machine learning. Yet, much like cooking, training SSL methods is a delicate art wi…
Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective
Avi Schwarzschild, Max Cembalest, Karthik Rao +2
As neural networks increasingly make critical decisions in high-stakes settings, monitoring and explaining their behavior in an understandable and trustworthy manner is a necessity…
Neural Auctions Compromise Bidder Information
Alex Stein, Avi Schwarzschild, Michael Curry +2
Single-shot auctions are commonly used as a means to sell goods, for example when selling ad space or allocating radio frequencies, however devising mechanisms for auctions with mu…
Universal Guidance for Diffusion Models
Arpit Bansal, Hong-Min Chu, Avi Schwarzschild +4
Typical diffusion models are trained to accept a particular form of conditioning, most commonly text, and cannot be conditioned on other modalities without retraining. In this work…