20 accepted papers
When language models are trained on textual data, they acquire both knowledge about the structure of language as well as knowledge of facts about the world. At inference time, their knowledge of facts can be leveraged to solve interesting problems and perform useful knowledge work for users. It is w…
AI-generated images have become pervasive, raising critical concerns around content authenticity, intellectual property, and the spread of misinformation. Invisible watermarks offer a promising solution for identifying AI-generated images, preserving content provenance without degrading visual quali…
Understanding what and how neural networks memorize during training is crucial, both from the perspective of unintentional memorization of potentially sensitive information and from the standpoint of effective knowledge acquisition for real-world, knowledge-intensive tasks. While previous studies pr…
Establishing character shape correspondence is a critical and fundamental task in computer vision and graphics, with diverse applications including re-topology, attribute transfer, and shape interpolation. Current dominant functional map methods, while effective in controlled scenarios, struggle in…
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-token training objective that we call the goldfish loss. During training, a randomly sampled subsets of tokens are excluded…
Recent breakthroughs in diffusion models have exhibited exceptional image-generation capabilities. However, studies show that some outputs are merely replications of training data. Such replications present potential legal challenges for model owners, especially when the generated content contains p…
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 finetuning of LLaMA-2-7B using Alpaca achieves $29.79$\% on AlpacaEval, which rises to $64.69$\% using noisy embeddings.…
As LLMs become commonplace, machine-generated text has the potential to flood the internet with spam, social media bots, and valueless content. _Watermarking_ is a simple and effective strategy for mitigating such harms by enabling the detection and documentation of LLM-generated text. Yet a crucial…
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 checkpoints on the web poses considerable risks, including the vulnerability to backdoor attacks. In this paper, we unveil a…
In the burgeoning age of generative AI, watermarks act as identifiers of provenance and artificial content. We present WAVES (Watermark Analysis via Enhanced Stress-testing), a benchmark for assessing image watermark robustness, overcoming the limitations of current evaluation methods. WAVES integra…
Potential harms of large language models can be mitigated by watermarking model output, i.e., embedding signals into generated text that are invisible to humans but algorithmically detectable from a short span of tokens. We propose a watermarking framework for proprietary language models. The waterm…
As industrial applications are increasingly automated by machine learning models, enforcing personal data ownership and intellectual property rights requires tracing training data back to their rightful owners. Membership inference algorithms approach this problem by using statistical techniques to…
Privacy is a central tenet of Federated learning (FL), in which a central server trains models without centralizing user data. However, gradient updates used in FL can leak user information. While the most industrial uses of FL are for text applications (e.g. keystroke prediction), the majority of…
The strength of modern generative models lies in their ability to be controlled through prompts. Hard prompts comprise interpretable words and tokens, and are typically hand-crafted by humans. Soft prompts, on the other hand, consist of continuous feature vectors. These can be discovered using pow…
Decentralized training of machine learning models, for instance with federated learning protocols, continues to diffuse from theory toward practical applications and use cases. In federated learning (FL), a central server trains a model collaboratively with a group of users by communicating model up…
Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. In this paper, we introduce a novel technique called Tree-Ring Watermarking that robustly fingerprints diffusion model outputs. Unlike existing methods…
Federated learning (FL) has rapidly risen in popularity due to its promise of privacy and efficiency. Previous works have exposed privacy vulnerabilities in the FL pipeline by recovering user data from gradient updates. However, existing attacks fail to address realistic settings because they either…
Many learning-based approaches have difficulty scaling to unseen data, as the generality of its learned prior is limited to the scale and variations of the training samples. This holds particularly true with 3D learning tasks, given the sparsity of 3D datasets available. We introduce a new learning…
Shape modeling and reconstruction from raw point clouds of objects stand as a fundamental challenge in vision and graphics research. Classical methods consider analytic shape priors; however, their performance is degraded when the scanned points deviate from the ideal conditions of cleanness and com…
The problem of adversarial examples has shown that modern Neural Network (NN) models could be rather fragile. Among the more established techniques to solve the problem, one is to require the model to be \emph{$\epsilon$-adversarially robust} (AR); that is, to require the model not to change predict…