26 citations · 65 across the 10 of their papers we have counts for
5 papers · 1 filter
What Does It Mean to Break a Distillation Defense?
Lena Libon, Pura Peetathawatchai, Michael Aerni +2
Black-box LLMs (accessible only via API) are vulnerable to distillation attacks, in which an attacker queries the model and trains a student on its outputs. A recent line of work p…
Large-scale online deanonymization with LLMs
Simon Lermen, Daniel Paleka, Joshua Swanson +3
We show that large language models can be used to perform at-scale deanonymization. With full Internet access, our agent can re-identify Hacker News users and Anthropic Interviewer…
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
Edoardo Debenedetti, Javier Rando, Daniel Paleka +18
Large language model systems face important security risks from maliciously crafted messages that aim to overwrite the system's original instructions or leak private data. To study…
Stealing Part of a Production Language Model
Nicholas Carlini, Daniel Paleka, Krishnamurthy Dj Dvijotham +11
We introduce the first model-stealing attack that extracts precise, nontrivial information from black-box production language models like OpenAI's ChatGPT or Google's PaLM-2. Speci…
Poisoning Web-Scale Training Datasets is Practical
Nicholas Carlini, Matthew Jagielski, Christopher A. Choquette-Choo +6
Deep learning models are often trained on distributed, web-scale datasets crawled from the internet. In this paper, we introduce two new dataset poisoning attacks that intentionall…