7 accepted papers
Machine Learning (ML) models have significant potential across research and industry to enable data-driven insights and decision-making. Their performance relies on input data quality, but real-world datasets often contain imperfections, making data preprocessing essential yet time-consuming. Our re
Growing concerns over the theft and misuse of Large Language Models (LLMs) underscore the need for effective fingerprinting to link a model to its original version and detect misuse. We define five essential properties for a successful fingerprint: Transparency, Efficiency, Persistence, Robustness,…
Recently, autonomous agents built on large language models (LLMs) have experienced significant development and are being deployed in real-world applications. Through the usage of tools, these systems can perform actions in the real world. Given the agents’ practical applications and ability to execu
Reasoning-focused LLMs sometimes alter their behavior when they detect that they are being evaluated—which can lead them to optimize for test-passing performance or to comply more readily with harmful prompts if real-world consequences appear absent. We present the first quantitative study of how su…
Large language model systems face significant security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study this problem, we organized a capture-the-flag competition at IEEE SaTML 2024, where the flag is a secret string in th…
Generative Adversarial Networks (GANs) have become widely used in model training, as they can improve performance and/or protect sensitive information by generating data. However, this also raises potential risks, as malicious GANs may compromise or sabotage models by poisoning their training data.…
Algorithms such as Differentially Private SGD enable training machine learning models with formal privacy guarantees. However, because these guarantees hold with respect to unrealistic adversaries, the protection afforded against practical attacks is typically much better. An emerging strand of work…