activity
20202024
most citedBaseline Defenses for Adversarial Attacks Against Aligned Language Models

37 citations · 86 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CV20241 cited

Detecting, Explaining, and Mitigating Memorization in Diffusion Models

Yuxin Wen, Yuchen Liu, Chen Chen +1

Recent breakthroughs in diffusion models have exhibited exceptional image-generation capabilities. However, studies show that some outputs are merely replications of training data.…

cs.CL2024

GenQA: Generating Millions of Instructions from a Handful of Prompts

Jiuhai Chen, Rifaa Qadri, Yuxin Wen +4

Most public instruction finetuning datasets are relatively small compared to the closed source datasets used to train industry models. To study questions about finetuning at scale,…

cs.CR20241 cited

Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models

Yuxin Wen, Leo Marchyok, Sanghyun Hong +3

It is commonplace to produce application-specific models by fine-tuning large pre-trained models using a small bespoke dataset. The widespread availability of foundation model chec…

cs.LG20244 cited

Coercing LLMs to do and reveal (almost) anything

Jonas Geiping, Alex Stein, Manli Shu +3

It has recently been shown that adversarial attacks on large language models (LLMs) can "jailbreak" the model into making harmful statements. In this work, we argue that the spectr…

cs.CL202314 cited

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…

cs.LG202337 cited

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…