100 citations · 328 across the 45 of their papers we have counts for
3 papers · 1 filter
Query-Based Adversarial Prompt Generation
Jonathan Hayase, Ema Borevkovic, Nicholas Carlini +2
Recent work has shown it is possible to construct adversarial examples that cause an aligned language model to emit harmful strings or perform harmful behavior. Existing attacks wo…
Are aligned neural networks adversarially aligned?
Nicholas Carlini, Milad Nasr, Christopher A. Choquette-Choo +8
Large language models are now tuned to align with the goals of their creators, namely to be "helpful and harmless." These models should respond helpfully to user questions, but ref…
Synthetic Query Generation for Privacy-Preserving Deep Retrieval Systems using Differentially Private Language Models
Aldo Gael Carranza, Rezsa Farahani, Natalia Ponomareva +3
We address the challenge of ensuring differential privacy (DP) guarantees in training deep retrieval systems. Training these systems often involves the use of contrastive-style los…