Papers

Filtered to threat modeling · clear filter

Browse by term

continual learning 33reinforcement learning 21large language models 9vision-language models 8language models 6benchmarking 5autoregressive models 4diffusion transformers 4generative models 4multimodal learning 4robotics 4video generation 4benchmarks 3computer vision 3policy optimization 3self-distillation 3vision-language-action models 3world modeling 3agent-based systems 2autonomous agents 2calibration 2coding agents 2diffusion models 2foundation models 2image synthesis 2in-context learning 2knowledge graphs 2LLMs 2multimodal evaluation 2multimodal large language models 2

Matching papers

Self-State Attacks on Self-Hosted AI Agents: How Far Can OS Defenses Go?

3 upvotes · 20 JUL 2026 · Yimeng Chen, Nathanaël Denis, Roberto Di Pietro et al.

This paper investigates how operating system (OS) defenses can prevent self-state attacks on self-hosted AI agents, which involve compromising an agent's own memory and configuration files. Practitioners caring about AI agent security should consider the limitations of current OS defenses against these types of attacks.

AI agent securityself-state attacksoperating system defensesthreat modelingattack surfacedefence strategies