most citedAdversarial Agents: Black-Box Evasion Attacks with Reinforcement Learning

1 citations · 1 across the 1 of their papers we have counts for

collaborators

6 papers

cs.CR20261 cited

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…

cs.CR2026

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…

cs.LG2025

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…

cs.CR2025

Efficient Storage Integrity in Adversarial Settings

Quinn Burke, Ryan Sheatsley, Yohan Beugin +4

Storage integrity is essential to systems and applications that use untrusted storage (e.g., public clouds, end-user devices). However, known methods for achieving storage integrit…

cs.CV2025

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…

cs.CR2025

On Scalable Integrity Checking for Secure Cloud Disks

Quinn Burke, Ryan Sheatsley, Rachel King +3

Merkle hash trees are the standard method to protect the integrity and freshness of stored data. However, hash trees introduce additional compute and I/O costs on the I/O critical…