1 citations · 1 across the 6 of their papers we have counts for
8 papers
The Limits of Information-Flow Control Enforcement for Agentic Systems
Jonathan Gregory, Kyle Domico, Kunyang Li +2
Information-flow control (IFC) is a promising approach to enforce policy in agentic AI systems. However, IFC suffers from label creep, a phenomenon where monotonically increasing s…
Longitudinal Analyses of SAST Tools: A CodeQL Case Study
Jean-Charles Noirot Ferrand, Kyle Domico, Yohan Beugin +1
Open-source software (OSS) pipelines rely on automated static analysis tools to prevent the introduction of vulnerabilities in code. However, there is limited understanding of the…
The Role of Learning in Attacking ML-based Network Intrusion Detection
Kyle Domico, Jean-Charles Noirot Ferrand, Patrick McDaniel
Machine Learning-based Network Intrusion Detection Systems (ML-NIDS) can be bypassed by rudimentary adversarial perturbations. Recent work has focused on identifying where such per…
LibIHT: A Hardware-Based Approach to Efficient and Evasion-Resistant Dynamic Binary Analysis
Changyu Zhao, Yohan Beugin, Jean-Charles Noirot Ferrand +3
Dynamic program analysis is invaluable for malware detection, debugging, and performance profiling. However, software-based instrumentation incurs high overhead and can be evaded b…
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…
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…
The Efficacy of Transformer-based Adversarial Attacks in Security Domains
Kunyang Li, Kyle Domico, Jean-Charles Noirot Ferrand +1
Today, the security of many domains rely on the use of Machine Learning to detect threats, identify vulnerabilities, and safeguard systems from attacks. Recently, transformer archi…