Attack Type

Extraction Research

Techniques for extracting sensitive information from models

1 matching entry out of 101 in this category

Extraction research results

1 entry

Deleted agent memory persists in live execution state

Published Sep 4, 2026Analyzed Sep 9, 2026Source: arXiv

Deleting a memory record can leave its information in an agent's summaries, pending plans and KV cache. The paper evaluates revocation across this derived execution state.

Forgetting Without Restarting: Execution-State Unlearning for Stateful LLM Agents

Evaluated models: Llama 3.1 8B Instruct, Qwen 2.5 7B Instruct, Mistral 7B Instruct v0.3

Related research categories