Search Results for author:
Found 6 papers, 4 papers with code
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
To address these challenges, we introduce JailbreakBench, an open-sourced benchmark with the following components: (1) a new jailbreaking dataset containing 100 unique behaviors, which we call JBB-Behaviors; (2) an evolving repository of state-of-the-art adversarial prompts, which we refer to as jailbreak artifacts; (3) a standardized evaluation framework that includes a clearly defined threat model, system prompts, chat templates, and scoring functions; and (4) a leaderboard that tracks the performance of attacks and defenses for various LLMs.
Scaling Compute Is Not All You Need for Adversarial Robustness
Finally, we make our benchmarking framework (built on top of \texttt{timm}~\citep{rw2019timm}) publicly available to facilitate future analysis in efficient robust deep learning.
Privacy Side Channels in Machine Learning Systems
Most current approaches for protecting privacy in machine learning (ML) assume that models exist in a vacuum, when in reality, ML models are part of larger systems that include components for training data filtering, output monitoring, and more.
Evading Black-box Classifiers Without Breaking Eggs
We then design new attacks that reduce the number of bad queries by $1. 5$-$7. 3\times$, but often at a significant increase in total (non-bad) queries.
A Light Recipe to Train Robust Vision Transformers
Additionally, investigating the reasons for the robustness of our models, we show that it is easier to generate strong attacks during training when using our recipe and that this leads to better robustness at test time.
RobustBench: a standardized adversarial robustness benchmark
As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it hard to identify the most promising ideas in training robust models.
