6 papers
Adversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning
Kyle Domico, Jean-Charles Noirot Ferrand, Ryan Sheatsley +3
Attacks on machine learning models have been extensively studied through stateless optimization. In this paper, we demonstrate how a reinforcement learning (RL) agent can learn a n…
Targeting Alignment: Extracting Safety Classifiers of Aligned LLMs
Jean-Charles Noirot Ferrand, Yohan Beugin, Eric Pauley +2
Alignment in large language models (LLMs) is used to enforce guidelines such as safety. Yet, alignment fails in the face of jailbreak attacks that modify inputs to induce unsafe ou…
On the Robustness Tradeoff in Fine-Tuning
Kunyang Li, Jean-Charles Noirot Ferrand, Ryan Sheatsley +4
Fine-tuning has become the standard practice for adapting pre-trained models to downstream tasks. However, the impact on model robustness is not well understood. In this work, we c…
Alignment and Adversarial Robustness: Are More Human-Like Models More Secure?
Blaine Hoak, Kunyang Li, Patrick McDaniel
A small but growing body of work has shown that machine learning models which better align with human vision have also exhibited higher robustness to adversarial examples, raising…
On Synthetic Texture Datasets: Challenges, Creation, and Curation
Blaine Hoak, Patrick McDaniel
The influence of textures on machine learning models has been an ongoing investigation, specifically in texture bias/learning, interpretability, and robustness. However, due to the…
Err on the Side of Texture: Texture Bias on Real Data
Blaine Hoak, Ryan Sheatsley, Patrick McDaniel
Bias significantly undermines both the accuracy and trustworthiness of machine learning models. To date, one of the strongest biases observed in image classification models is text…