# RedEdit: Agentic Red-Teaming of Image Safety Classifiers via MCTS-Guided Photo-Editing

arXiv: https://arxiv.org/abs/2606.06140 · HTML: https://mlsanity.com/paper/2606.06140/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 21 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)
- LLM safety and security / [Vision-language and text-to-image safety](https://mlsanity.com/safety/vision-language-and-text-to-image-safety/)

## Builds on (most cited first, 13 of 13)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Red-Teaming the Stable Diffusion Safety Filter](https://mlsanity.com/paper/2210.04610/) (2022)
- [Ring-A-Bell! How Reliable are Concept Removal Methods for Diffusion Models?](https://mlsanity.com/paper/2310.10012/) (2023)
- [MMA-Diffusion: MultiModal Attack on Diffusion Models](https://mlsanity.com/paper/2311.17516/) (2023)
- [SneakyPrompt: Jailbreaking Text-to-image Generative Models](https://mlsanity.com/paper/2305.12082/) (2023)
- [Can Machines Help Us Answering Question 16 in Datasheets, and In Turn Reflecting on Inappropriate Content?](https://mlsanity.com/paper/2202.06675/) (2022)
- [T2ISafety: Benchmark for Assessing Fairness, Toxicity, and Privacy in Image Generation](https://mlsanity.com/paper/2501.12612/) (2025)
- [IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves](https://mlsanity.com/paper/2411.00827/) (2024)
- [Distraction is All You Need for Multimodal Large Language Model Jailbreaking](https://mlsanity.com/paper/2502.10794/) (2025)
- [ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users](https://mlsanity.com/paper/2405.19360/) (2024)
- [Red-Teaming Text-to-Image Systems by Rule-based Preference Modeling](https://mlsanity.com/paper/2505.21074/) (2025)
- [TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration](https://mlsanity.com/paper/2603.22882/) (2026)

## Abstract (arXiv)

Image safety classifiers serve as a critical component of contemporary content moderation systems on the internet. However, their resilience against user-style malicious image editing remains underexplored. Such behaviors are highly prevalent in daily scenarios but difficult to fully reproduce. To explore this vulnerability, we introduce RedEdit, a novel black-box red-teaming agent that formulates photo-editing evasion as a combinatorial search problem over edit-tool sequences. It adopts a Vision-Language-Model (VLM)-based proposer to generate semantically targeted candidate edits and a Monte Carlo Tree Search (MCTS) planner to prioritize promising edit paths while backtracking from ineffective ones. Together, the proposer and planner instantiate two key capabilities of human attackers, i.e., domain knowledge and iterative backtracking, respectively, to reproduce this practical threat. Our extensive experiments on UnsafeBench reveal profound systemic vulnerabilities: fewer than two edits on average enable 76.2% of unsafe images to evade detectors, while retaining 93.0% malicious semantics, meaning that such manipulated content remains perceptually malicious to humans while easily bypassing automated moderation. We therefore appeal to the community for more attention to this overlooked practical threat.