18 accepted papers
Large language models are susceptible to memorizing repeated sequences, posing privacy and copyright concerns. A popular mitigation strategy is to remove memorized information from specific neurons post-hoc. However, such approaches have shown limited success so far. In a controlled setting, we show…
Robust unlearning is crucial for safely deploying large language models (LLMs) in environments where data privacy, model safety, and regulatory compliance must be ensured. Yet the task is inherently challenging, partly due to difficulties in reliably measuring whether unlearning has truly occurred.…
Given how large parts of publicly available text are crawled to pretrain large language models (LLMs), data creators increasingly worry about the inclusion of their proprietary data for model training without attribution or licensing. Their concerns are also shared by benchmark curators whose test-s…
As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during pretraining, they are hard to remove. In this work, we prese…
The remarkable capabilities of Large Language Models (LLMs) can be mainly attributed to their massive training datasets, which are often scraped from the internet without respecting data owners’ intellectual property rights. Dataset Inference (DI) offers a potential remedy by identifying whether a s…
The proliferation of large language models (LLMs) in the real world has come with a rise in copyright cases against companies for training their models on unlicensed data from the internet. Recent works have presented methods to identify if individual text sequences were members of the model's train…
Large language models are trained on massive scrapes of the web, which are often unstructured, noisy, and poorly phrased. Current scaling laws show that learning from such data requires an abundance of both compute and data, which grows with the size of the model being trained. This is infeasible bo…
Large language models (LLMs) trained on web-scale datasets raise substantial concerns regarding permissible data usage. One major question is whether these models "memorize" all their training data or they integrate many data sources in some way more akin to how a human would learn and synthesize i…
Vision-language models (VLMs) are trained for thousands of GPU hours on carefully selected subsets of massive web scrapes. For instance the LAION public dataset retained only about 10 percent of the total crawled data. In recent times data curation has gained prominence with several works developing…
Large web-crawled multimodal datasets have powered a slew of new methods for learning general-purpose visual representations, advancing the state of the art in computer vision and revolutionizing zero- and few-shot recognition. One crucial decision facing practitioners is how, if at all, to curate t…
Colloquially speaking, image generation models based upon diffusion processes are frequently said to exhibit ''hallucinations'' samples that could never occur in the training data. But where do such hallucinations come from? In this paper, we study a particular failure mode in diffusion models, whi…
Recent efforts at explaining the interplay of memorization and generalization in deep overparametrized networks have posited that neural networks *memorize* ``hard'' examples in the final few layers of the model. Memorization refers to the ability to correctly predict on *atypical* examples of the t…
In recent years, NLP practitioners have converged on the following practice: (i) import an off-the-shelf pretrained (masked) language model; (ii) append a multilayer perceptron atop the CLS token's hidden representation (with randomly initialized weights); and (iii) fine-tune the entire model on a d…
Researchers investigating example hardness have increasingly focused on the dynamics by which neural networks learn and forget examples throughout training. Popular metrics derived from these dynamics include (i) the epoch at which examples are first correctly classified; (ii) the number of times th…
Recent works in adversarial robustness have proposed defenses to improve the robustness of a single model against the union of multiple perturbation types. However, these methods still suffer significant trade-offs compared to the ones specifically trained to be robust against a single perturbation…
Current model extraction attacks assume that the adversary has access to a surrogate dataset with characteristics similar to the proprietary data used to train the victim model. This requirement precludes the use of existing model extraction techniques on valuable models, such as those trained on ra…
With increasingly more data and computation involved in their training, machine learning models constitute valuable intellectual property. This has spurred interest in model stealing, which is made more practical by advances in learning with partial, little, or no supervision. Existing defenses foc…
Owing to the susceptibility of deep learning systems to adversarial attacks, there has been a great deal of work in developing (both empirically and certifiably) robust classifiers. While most work has defended against a single type of attack, recent work has looked at defending against multiple per…