# Memory Control Flow Attack (Override) on MEMFLOW Override

Source: [Memory Control Flow Attack (Override) on MEMFLOW Override](<https://www.sota2.com/research/sota/memory-control-flow-attack-override-on-memflow-override>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-17T06:39:52.391Z

Evaluation of model performance against memory control flow override attacks using the MEMFLOW Override dataset, measured by Attack Success Rate (ASR) and Instruction Success Rate (ISR).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Memory Control Flow Attack (Override) |
| Dataset (including any stated split) | MEMFLOW Override |
| Metric | ISR |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 30 of 30 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [ISR](<https://www.sota2.com/research/sota/memory-control-flow-attack-override-on-memflow-override.md?metric=ISR>): Higher is better; unit: PERCENT.

- [ASR](<https://www.sota2.com/research/sota/memory-control-flow-attack-override-on-memflow-override.md?metric=ASR>): Lower is better; unit: PERCENT.

## Recorded results

| Method | ISR | Result date | Report paper |
| --- | --- | --- | --- |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 100 | Not recorded | 69b8e0620636e5bf4afbf051 |
| MEMFLOW | 97.2 | Not recorded | 69b8e0620636e5bf4afbf051 |

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd28.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd2a.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd2b.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd2c.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd2d.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd2e.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Neutral","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd2f.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Neutral","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd30.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Neutral","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd31.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Neutral","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd32.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Neutral","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd33.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Neutral","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd34.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"None","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd35.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"None","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd36.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"None","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd37.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"None","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd38.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"None","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd39.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"None","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd3a.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Weak","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd3b.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Weak","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd3c.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Weak","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd3d.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Weak","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd3e.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Weak","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd3f.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Weak","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd40.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"OFF","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd41.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"OFF","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd42.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"OFF","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd43.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"OFF","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gpt-5-mini"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd44.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"OFF","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 100. Result ID: 69b8f69547f34ce924a0cd45.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"OFF","Regime":"Isolated","Framework":"LlamaIndex","LLM Backbone":"gemini-2.5-flash"}. This record does not assert independent reproduction.

### MEMFLOW

ISR: 97.2. Result ID: 69b8f69547f34ce924a0cd29.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0620636e5bf4afbf051.md>)

Recorded evaluation configuration: {"Tool Target":"Safe Tool","Tool Label":"Harmful","Retrieval Strength":"Strong","Regime":"Isolated","Framework":"LangChain","LLM Backbone":"claude-sonnet-4-5"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
