This work identifies 18 foundational challenges in assuring the alignment and safety of large
language models (LLMs). These challenges are organized into three different categories …

Despite the widespread adoption of prompting, prompt tuning and prefix-tuning of
transformer models, our theoretical understanding of these fine-tuning methods remains …

We construct pseudorandom error-correcting codes (or simply pseudorandom codes), which
are error-correcting codes with the property that any polynomial number of codewords are …

We show the viability of tackling misuses of large language models beyond the identification
of machine-generated text. While existing zero-bit watermark methods focus on detection …

As ML models become increasingly complex and integral to high-stakes domains such as
finance and healthcare, they also become more susceptible to sophisticated adversarial …

Steganography is the technique of hiding secret messages within seemingly harmless
covers to elude examination by censors. Despite having been proposed several decades …

The development of privacy-enhancing technologies has made immense progress in
reducing trade-offs between privacy and performance in data exchange and analysis …

Given a set of discrete probability distributions, the minimum entropy coupling is the
minimum entropy joint distribution that has the input distributions as its marginals. This has …

We introduce a cryptographic method to hide an arbitrary secret payload in the response of
a Large Language Model (LLM). A secret key is required to extract the payload from the …

The rapid proliferation of frontier model agents promises significant societal advances but
also raises concerns about systemic risks arising from unsafe interactions. Collusion to the …