Cover Image

Optimizing AI Agent Attacks With Synthetic Data

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Loughridge, Chloe, Colognese, Paul, Griffin, Avery, Tracy, Tyler, Kutasov, Jon, Benton, Joe
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Evaluating Control Protocols for Untrusted AI Agents
by: Kutasov, Jon, et al.
Published: (2025)

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors
by: Najt, Elle, et al.
Published: (2026)

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents
by: Kutasov, Jonathan, et al.
Published: (2025)

dafny-annotator: AI-Assisted Verification of Dafny Programs
by: Poesia, Gabriel, et al.
Published: (2024)

Model Spec Midtraining: Improving How Alignment Training Generalizes
by: Li, Chloe, et al.
Published: (2026)

Efficiently Aligning Language Models with Online Natural Language Feedback
by: Ye, Christine, et al.
Published: (2026)

Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring
by: Schaeffer, Joachim, et al.
Published: (2026)

Singular Vectors of Attention Heads Align with Features
by: Franco, Gabriel, et al.
Published: (2026)

BashArena: A Control Setting for Highly Privileged AI Agents
by: Kaufman, Adam, et al.
Published: (2025)

MonitoringBench: Semi-Automated Red-Teaming for Agent Monitoring
by: Jotautaitė, Monika, et al.
Published: (2026)

Toward a Trustworthy Optimization Modeling Agent via Verifiable Synthetic Data Generation
by: Lima, Vinicius, et al.
Published: (2025)

Measuring AI Agents' Progress on Multi-Step Cyber Attack Scenarios
by: Folkerts, Linus, et al.
Published: (2026)

Generative AI in clinical practice: novel qualitative evidence of risk and responsible use of Google's NotebookLM
by: Reuter, Max, et al.
Published: (2025)

When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models
by: Mustaqim, S. M., et al.
Published: (2025)

Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
by: Turpin, Miles, et al.
Published: (2025)

Removing Sandbagging in LLMs by Training with Weak Supervision
by: Ryd, Emil, et al.
Published: (2026)

AgentSGEN: Multi-Agent LLM in the Loop for Semantic Collaboration and GENeration of Synthetic Data
by: Xuan, Vu Dinh, et al.
Published: (2025)

Combining Cost-Constrained Runtime Monitors for AI Safety
by: Hua, Tim Tian, et al.
Published: (2025)

Superplatforms Have to Attack AI Agents
by: Lin, Jianghao, et al.
Published: (2025)

Securing AI Agents Against Prompt Injection Attacks
by: Ramakrishnan, Badrinath, et al.
Published: (2025)

Emerging Cyber Attack Risks of Medical AI Agents
by: Qiu, Jianing, et al.
Published: (2025)

Automatically Attacking Software Reverse Engineering AI Agents
by: Crawford, Brian, et al.
Published: (2026)

From Assistant to Double Agent: Formalizing and Benchmarking Attacks on OpenClaw for Personalized Local AI Agent
by: Wang, Yuhang, et al.
Published: (2026)

CI-Bench: Benchmarking Contextual Integrity of AI Assistants on Synthetic Data
by: Cheng, Zhao, et al.
Published: (2024)

ATAG: AI-Agent Application Threat Assessment with Attack Graphs
by: Gandhi, Parth Atulbhai, et al.
Published: (2025)

Repurposing Synthetic Data for Fine-grained Search Agent Supervision
by: Zhao, Yida, et al.
Published: (2025)

Linguistic and Argument Diversity in Synthetic Data for Function-Calling Agents
by: Greenstein, Dan, et al.
Published: (2026)

Professional Software Developers Don't Vibe, They Control: AI Agent Use for Coding in 2025
by: Huang, Ruanqianqian, et al.
Published: (2025)

TO-Agents: A Multi-Agent AI Pipeline for Preference-Guided Topology Optimization
by: Stewart, Isabella A., et al.
Published: (2026)

Natural Emergent Misalignment from Reward Hacking in Production RL
by: MacDiarmid, Monte, et al.
Published: (2025)

Generative Models for Synthetic Data: Transforming Data Mining in the GenAI Era
by: Li, Dawei, et al.
Published: (2025)

Polysemanticity and Capacity in Neural Networks
by: Scherlis, Adam, et al.
Published: (2022)

Synthetic Data for Robust AI Model Development in Regulated Enterprises
by: Godbole, Aditi
Published: (2025)

Template-as-Ontology: Configurable Synthetic Data Infrastructure for Cross-Domain Manufacturing AI Validation
by: Chethan, Grama
Published: (2026)

Synthetic Trust Attacks: Modeling How Generative AI Manipulates Human Decisions in Social Engineering Fraud
by: Ashraf, Muhammad Tahir
Published: (2026)

SymptomWise: A Deterministic Reasoning Layer for Reliable and Efficient AI Systems
by: Henry, Isaac, et al.
Published: (2026)

Bypassing AI Control Protocols via Agent-as-a-Proxy Attacks
by: Isbarov, Jafar, et al.
Published: (2026)

Internal Deployment Gaps in AI Regulation
by: Kwon, Joe, et al.
Published: (2026)

Optimsyn: Influence-Guided Rubrics Optimization for Synthetic Data Generation
by: Fan, Zhiting, et al.
Published: (2026)

Kinematic Tokenization: Optimization-Based Continuous-Time Tokens for Learnable Decision Policies in Noisy Time Series
by: Kearney, Griffin
Published: (2026)