Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

1 code implementation • 4 Dec 2023 • Anay Mehrotra, Manolis Zampetakis, Paul Kassianik, Blaine Nelson, Hyrum Anderson, Yaron Singer, Amin Karbasi

In addition, before sending prompts to the target, TAP assesses them and prunes the ones unlikely to result in jailbreaks, reducing the number of queries sent to the target LLM.

Navigate

Poisoning Web-Scale Training Datasets is Practical

1 code implementation • 20 Feb 2023 • Nicholas Carlini, Matthew Jagielski, Christopher A. Choquette-Choo, Daniel Paleka, Will Pearce, Hyrum Anderson, Andreas Terzis, Kurt Thomas, Florian Tramèr

Deep learning models are often trained on distributed, web-scale datasets crawled from the internet.

Data Poisoning

Metadata-Based Detection of Child Sexual Abuse Material

no code implementations • 5 Oct 2020 • Mayana Pereira, Rahul Dodhia, Hyrum Anderson, Richard Brown

With such restrictions in place, the development of CSAM machine learning detection systems based on file metadata uncovers several opportunities.

BIG-bench Machine Learning

KiloGrams: Very Large N-Grams for Malware Classification

1 code implementation • 1 Aug 2019 • Edward Raff, William Fleming, Richard Zak, Hyrum Anderson, Bill Finlayson, Charles Nicholas, Mark McLean

N-grams have been a common tool for information retrieval and machine learning applications for decades.

Classification General Classification +4

The Malicious Use of Artificial Intelligence: Forecasting, Prevention, and Mitigation

no code implementations • 20 Feb 2018 • Miles Brundage, Shahar Avin, Jack Clark, Helen Toner, Peter Eckersley, Ben Garfinkel, Allan Dafoe, Paul Scharre, Thomas Zeitzoff, Bobby Filar, Hyrum Anderson, Heather Roff, Gregory C. Allen, Jacob Steinhardt, Carrick Flynn, Seán Ó hÉigeartaigh, SJ Beard, Haydn Belfield, Sebastian Farquhar, Clare Lyle, Rebecca Crootof, Owain Evans, Michael Page, Joanna Bryson, Roman Yampolskiy, Dario Amodei

This report surveys the landscape of potential security threats from malicious uses of AI, and proposes ways to better forecast, prevent, and mitigate these threats.